sneak/prompts
1
0
Fork 0
Code Issues 18 Pull Requests 4 Actions Packages Projects Releases Wiki Activity

Compare commits

base: sneak:33fb5dde980c93ec21e05f3c1ba3acc3405ac302
Branches Tags
sneak:main sneak:fix/25-gomodguard-v2 sneak:next sneak:go-test-count1 sneak:lint-policy-reconcile sneak:llm-prose-tells-v10 sneak:llm-prose-tells-merge-pass sneak:llm-prose-tells-final sneak:llm-prose-tells-checklist-pass sneak:llm-prose-tells-updates sneak:add-llm-prose-tells sneak:improve-quickstart-commands
..
compare: sneak:add-llm-prose-tells
Branches Tags
sneak:fix/25-gomodguard-v2 sneak:main sneak:next sneak:go-test-count1 sneak:lint-policy-reconcile sneak:llm-prose-tells-v10 sneak:llm-prose-tells-merge-pass sneak:llm-prose-tells-final sneak:llm-prose-tells-checklist-pass sneak:llm-prose-tells-updates sneak:add-llm-prose-tells sneak:improve-quickstart-commands

3 Commits
33fb5dde98 ... add-llm-pr

Author SHA1 Message Date
user
c9af95d99e add lol section with conversation excerpts
Some checks failed
check / check (push) Failing after 5s
Details
2026-03-04 14:15:38 -08:00
user
a6fb657d0e fix staccato/parallel tell in dramatic fragment section
All checks were successful
check / check (push) Successful in 11s
Details
2026-03-04 14:13:42 -08:00
user
7b22e6757d add two-clause compound sentence and almost-hedge patterns, fix instances throughout
All checks were successful
check / check (push) Successful in 12s
Details
2026-03-04 14:09:22 -08:00
26 changed files with 261 additions and 2040 deletions
Expand all files Collapse all files

98
.dockerignore
View File

@@ -1,97 +1,3 @@
# Docker matches this file with moby/patternmatcher: Go filepath.Match
# semantics plus a `**` extension, compiled to a regexp. Plain
# filepath.Match has no `**` at all. What follows from that: `*` does not
# cross `/`, and a pattern without a leading `**/` is anchored at the
# build-context root. Every depth-independent pattern therefore needs the
# `**/` prefix — without it `config/.env` and `certs/server.key` still
# ship while the file reads as solved.
#
# Root-anchored entries are for paths that occur exactly once, at the
# context root. A host-built binary is the usual case, and it must be
# written anchored: `/myapp`, never `**/myapp`. The prefixed form also
# matches `cmd/myapp/`, which deletes the package directory from the
# context. In-repo agent scratch is the other case, for the same reason
# — with the caveat recorded at that entry: anchoring is exact only
# where agents run at the repo root, and a repo where they do not must
# add its own entries.
#
# Matching is case-sensitive, so `**/*.key` does not match
# `certs/SERVER.KEY`, which is reachable on the case-insensitive
# filesystems most laptops use. Adding an ALL-CAPS twin per pattern is
# not the fix: it still misses `Server.Key` while reading as though case
# were handled. Character ranges cover every spelling in one line, so
# every secret name below is written that way — including the
# extensionless SSH keys and `.envrc`, because on those same
# case-insensitive filesystems direnv reads `.ENVRC` and ssh reads
# `ID_RSA`.
#
# `**/*.[eE][nN][vV]` also excludes a committed env template such as
# `example.env`. If the build genuinely needs one, re-include it with a
# negation after the pattern: `!docs/example.env`.
#
# Extend this file with the repo's own host-built artifacts (compiled
# binaries, test binaries, coverage output); those are per-repo and
# belong here because a host build otherwise drops them into the
# context.
# Repository metadata: exactly one, at the context root. Excluding it
# means `git describe` cannot run in any build stage, and it fails
# quietly there rather than erroring, so a version embedded that way
# comes out empty. Compute the version on the host and pass it in with
# `--build-arg VERSION=...`; see the version rule in REPO_POLICIES.md.
.git
# In-repo agent scratch: a directory holding a full additional checkout
# of the repo for each in-flight agent. Anchored because it occurs
# exactly once *where agents run at the repo root*, which is the
# convention this file assumes; the `**/` form would also match any
# nested directory of that name and delete it from the build.
#
# KNOWN GAP, and it is not hypothetical: the directory is created in the
# agent's working directory. If agents in this repo run in
# subdirectories — a monorepo with a per-service agent, say — then
# `services/api/.claude/` is NOT excluded by the line below and still
# reaches the build context and the image, which is the exposure this
# entry exists to close. A repo in that shape adds its own anchored
# entries (`/services/api/.claude`), or `**/.claude` after confirming no
# legitimately named nested directory would be caught.
#
# Not case-folded, unlike the secret patterns below: tooling creates
# this directory in exactly one spelling, so a folded pattern would add
# no coverage.
.claude
# Environment files. `*.env` covers both the bare `.env` name (`*` matches
# the empty string) and the `prod.env` convention.
**/*.[eE][nN][vV]
**/.[eE][nN][vV].*
**/.[eE][nN][vV][rR][cC]
# Private keys and the bundles that carry them. Public certificates
# (*.crt, *.cer) are deliberately absent: they are not secrets and are
# sometimes a legitimate build input.
**/*.[pP][eE][mM]
**/*.[kK][eE][yY]
**/*.[pP]12
**/*.[pP][fF][xX]
**/[iI][dD]_[rR][sS][aA]
**/[iI][dD]_[dD][sS][aA]
**/[iI][dD]_[eE][cC][dD][sS][aA]
**/[iI][dD]_[eE][dD]25519
# Dependencies: restored inside the image, never copied in.
**/node_modules
# OS metadata.
**/.DS_Store
**/Thumbs.db
# Editor state. Never a build input, and it churns under a developer's
# hands, so it invalidates COPY for reasons unrelated to the source.
**/*.swp
**/*.swo
**/*~
**/*.bak
**/.idea
**/.vscode
**/*.sublime-*
node_modules
.DS_Store

2
.gitea/workflows/check.yml
View File

@@ -6,4 +6,4 @@ jobs:
steps:
# actions/checkout v4.2.2, 2026-02-22
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
- run: script/cibuild
- run: docker build .

6
.gitignore vendored
View File

@@ -11,12 +11,6 @@ Thumbs.db
.vscode/
*.sublime-*
# Agent scratch (worktrees of this repo, created and destroyed by
# in-flight tooling). Unanchored: .gitignore patterns already match at
# every depth, so no prefix is wanted here. This is not a .dockerignore
# entry and must not be given a `**/` prefix on the way into one.
.claude/
# Node
node_modules/

8
.golangci.yml
View File

@@ -1,9 +1,5 @@
version: "2"
# Config schema uses the golangci-lint v2 layout (settings live under
# linters.settings, not top-level linters-settings) so that the
# thresholds below are actually applied by golangci-lint >= v2.
run:
timeout: 5m
modules-download-mode: readonly
@@ -18,7 +14,8 @@ linters:
- wsl # Deprecated, replaced by wsl_v5
- wrapcheck # Too verbose for internal packages
- varnamelen # Short names like db, id are idiomatic Go
settings:
linters-settings:
lll:
line-length: 88
funlen:
@@ -30,5 +27,6 @@ linters:
threshold: 100
issues:
exclude-use-default: false
max-issues-per-linter: 0
max-same-issues: 0

25
Dockerfile
View File

@@ -1,28 +1,11 @@
# node 22-alpine, 2026-02-22
FROM node@sha256:e4bf2a82ad0a4037d28035ae71529873c069b13eb0455466ae0bc13363826e34
RUN apk add --no-cache make
WORKDIR /app
# script/bootstrap installs all prerequisites (make via apk here; node
# and yarn are already in the base image, so those steps are skipped).
# Dependency manifests are copied first so the bootstrap layer is
# cached until they change.
COPY script/ script/
COPY package.json yarn.lock ./
RUN script/bootstrap
RUN yarn install --frozen-lockfile
COPY . .
# CHECK_EPOCH is a per-invocation nonce supplied by script/cibuild and
# script/docker. Without it an unchanged tree serves this layer from
# cache and the build reports a green it never ran. ARG is stage-scoped,
# so it must be redeclared in every stage that runs checks. The guard
# makes a bare `docker build .` fail loudly instead of silently reusing
# the empty (and therefore stable) cache key. Expand the value into the
# command so the cache miss does not depend on BuildKit's handling of an
# unreferenced ARG. Both the guard and the check RUN reference the value,
# so both are value-keyed: there are two independent invalidation points
# here, not one. Keep both.
ARG CHECK_EPOCH
RUN [ -n "$CHECK_EPOCH" ] || exit 1
RUN echo "check epoch: ${CHECK_EPOCH}" && make check
RUN make check

35
Makefile
View File

@@ -1,32 +1,31 @@
.PHONY: bootstrap setup test lint fmt fmt-check check docker hooks
.PHONY: test lint fmt fmt-check check docker hooks
# Makefile targets are thin shims; the implementations live in script/
# per the scripts-to-rule-them-all pattern (see the Entrypoints section
# of README.md).
bootstrap:
@script/bootstrap
setup:
@script/setup
# flags are repeated here (also in .prettierrc) so this Makefile works
# standalone when copied as a template
PRETTIER := yarn run prettier
test:
@script/test
@echo "No tests defined."
lint:
@script/lint
@echo "Linting markdown files..."
@$(PRETTIER) --check '**/*.md' --tab-width 4 --prose-wrap always
fmt:
@script/fmt
@$(PRETTIER) --write '**/*.md' --tab-width 4 --prose-wrap always
fmt-check:
@script/fmt-check
@$(PRETTIER) --check '**/*.md' --tab-width 4 --prose-wrap always
check:
@script/check
check: test lint fmt-check
docker:
@script/docker
docker build -t prompts .
hooks:
@script/install-precommit
@printf '#!/bin/sh\nset -e\n' > .git/hooks/pre-commit
@if [ -f go.mod ]; then \
printf 'go mod tidy\ngo fmt ./...\ngit diff --exit-code -- go.mod go.sum || { echo "go mod tidy changed files; please stage and retry"; exit 1; }\n' >> .git/hooks/pre-commit; \
fi
@printf 'make check\n' >> .git/hooks/pre-commit
@chmod +x .git/hooks/pre-commit

35
README.md
View File

@@ -102,41 +102,6 @@ cd prompts
Prompts are stored as Markdown files in `prompts/`. Copy or reference them as
needed in your projects.
## Entrypoints
This repository adheres to the
[Scripts to Rule Them All](https://github.com/github/scripts-to-rule-them-all)
standard: normalized scripts in `script/` are the entrypoints for the
development workflow, and the Makefile targets are thin shims that call them.
The scripts are POSIX sh (not bash) so they run in minimal containers such as
alpine. We provide:
- `script/bootstrap` — install all dependencies (yarn install)
- `script/setup` — set up the repo for development after a fresh clone: runs
`script/bootstrap`, then `script/install-precommit`
- `script/projectname` — output the project name (our own extension); used by
`script/docker` for the image tag
- `script/test` — run the test suite (no tests defined here)
- `script/lint` — lint the markdown files with prettier
- `script/fmt` — format all markdown files with prettier (writes)
- `script/fmt-check` — check formatting (read-only)
- `script/check` — run all checks: `test`, `lint`, `fmt-check` (our own
extension)
- `script/docker` — build the Docker image, tagged via `script/projectname`
(byte-identical across repos); passes the same `CHECK_EPOCH` nonce as
`script/cibuild`
- `script/cibuild` — cd to the repo root, assign `epoch="$(date +%s%N)$$"`, then
`docker build --build-arg CHECK_EPOCH="$epoch" .` (what CI runs; the image
build runs `script/check`, and the per-invocation `CHECK_EPOCH` nonce is what
stops Docker serving that check from cache on an unchanged tree — a bare
`docker build .` fails closed on purpose)
- `script/precommit` — run by the git pre-commit hook (our own extension); calls
`script/check`
- `script/install-precommit` — installs the git pre-commit hook (our own
extension); `make hooks` shims to it
`make hooks` installs the pre-commit hook that runs `script/precommit`.
## Rationale
LLM prompts, especially development policies, benefit from version control and a

137
TODO.md
View File

@@ -1,137 +0,0 @@
# Workflow
- branch (from `main`)
- do the work in Next Step
- move Next Step to the top of Completed Steps
- move the top item of Future Steps into Next Step
- commit (`TODO.md` changes in the same commit as the work)
- merge to `main` if the branch is not protected, otherwise open a PR
- push
# Status
pre-1.0
# Next Step
Finish the two draft prompt documents in the working tree and commit them:
prompts/FIXUP_CLEAN.md (currently a near-empty stub) and prompts/FIXUP_REPORT.md
(a rough draft). Write the missing content, run `make fmt` so they pass
fmt-check, and commit.
# Completed Steps
- 2026-08-09: Made a golangci-lint result belong to the tree that asked for it.
REPO_POLICIES.md now carries the canonical Go `script/lint`, which gives the
linter per-checkout `GOLANGCI_LINT_CACHE` and per-checkout `TMPDIR`. The two
are separate defects and the second is the one that gets dropped: the result
cache is keyed on file content rather than location, so checkouts holding
identical files serve each other's findings under the other's path, while the
concurrency lock is `$TMPDIR/golangci-lint.lock` — host-global, independent of
the cache, and unaffected by isolating it. Moving workers from worktrees to
their own clones does not help either half; it only removes the foreign-path
artefact that made the defect visible. The lock error is retried rather than
surfaced, because it is not a result: it exits non-zero exactly as findings
do, and reporting it as findings sends a correct branch back for rework.
Detection is on the stderr stream and never on exit status, so a finding
quoting the lock message in source cannot be retried away, and exhaustion
exits 75 with a VOID message rather than passing or failing quietly.
`--allow-serial-runners` (which keeps the guard and queues) covers the
same-checkout overlap that `TMPDIR` scoping cannot; `--allow-parallel-runners`
is rejected outright. The stdout and stderr capture files are per invocation
rather than per checkout, because serialising the linter does not serialise
the shell's redirections: two runs in one checkout — the overlap the flag
exists to support — would otherwise truncate and read each other's output,
which is the same defect one layer above where it was fixed. Both checklists
gained the corresponding items, since a half-fix that sets only the cache
reads as complete. `GOCACHE` was measured and does not need isolating.
Verified with the snippet extracted from the committed document and executed
as a consuming repo would adopt it, against paired controls: contamination
reproduced on the pre-fix form and absent on the adopted one, retry engaged,
exhaustion loud, a genuine finding still reported, and a held host lock
failing the pre-fix script while leaving the adopted one untouched.
- 2026-08-09: Kept in-repo agent scratch out of the Docker build context and out
of version control. `.claude/` holds one worktree — an entire additional
checkout of the repo — per in-flight agent, and under `COPY . .` all of it was
reaching the image: another session's unreviewed, sometimes uncommitted work,
inflating the context by a multiple of the repo and invalidating `COPY` for
reasons unrelated to the repo's own content. The `.dockerignore` entry is
root-anchored, because the directory occurs exactly once where agents run at
the repo root and the `**/` form additionally deletes any nested directory of
that name — with the residual gap that follows from anchoring (a monorepo
running agents in subdirectories still ships `services/api/.claude/`) stated
in the canonical `.dockerignore`, the policy and the existing-repo checklist,
since consuming repos receive the files rather than the tracker; the
`.gitignore` entry is unanchored, because `.gitignore` patterns already match
at every depth, and each file is written to its own semantics rather than
derived from the other. Also closed the consequence that ships broken
silently: excluding `.git` means `git describe` cannot run in any build stage
and yields an empty version without erroring, so `script/docker` and
`script/cibuild` now compute the version on the host and pass
`--build-arg VERSION`, and `REPO_POLICIES.md` states where `VERSION` comes
from instead of leaving the reader to fill the gap with `git describe` inside
the build. The two Go documents that carry the `GOLDFLAGS` pattern were
corrected in the same pass, from `:=` to `?=`, since a `$(shell git describe)`
evaluated inside a build stage is exactly the empty version this closes.
Verified by enumerating a probe image before, after, and against the
`**/`-prefixed form, with a positive control and the `CHECK_EPOCH` cache
verification re-run under the changed build context.
- 2026-08-09: Closed the secret exposure in the canonical `.dockerignore`: a
developer's local `.env`, `*.pem` or `*.key` was reaching the Docker build
context under `COPY . .`, invisible to every git-based check because
`.gitignore` covers it. The patterns are written to `.dockerignore`'s own
`moby/patternmatcher` semantics — `**/`-prefixed so they hold at every depth,
which also fixes nested `node_modules` — rather than transplanted from
`.gitignore`, whose unprefixed form protects only the repository root while
reading as solved. Coverage extends past the `.env`/`.pem`/`.key` trio to the
`prod.env` convention, `.envrc`, PKCS#12 bundles and extensionless SSH keys,
every one of them case-folded with character ranges because matching is
case-sensitive and an ALL-CAPS twin per pattern still misses `Server.Key`.
`REPO_POLICIES.md` and both repo checklists now state that asymmetry and
require verification by enumerating the image rather than by reading the
patterns. Verified with a probe image before, against three naive forms
(unprefixed, lowercase-only, ALL-CAPS-doubled), and after.
- 2026-08-09: Made the pinned golangci-lint actually propagate: REPO_POLICIES.md
now carries the canonical `script/bootstrap` snippet for Go repos, which
installs when the installed version does not match the pin (the old
`if missing` guard tested PATH presence only, so pins were inert on any
provisioned machine and CI silently disagreed with local) and then re-resolves
the binary through `PATH` and fails loudly, naming the shadowing path, when
the install did not take effect — the failure mode the naive
compare-then-install fix leaves behind while reporting success.
- 2026-08-09: Fixed the false green in the canonical CI gate: `script/cibuild`
and `script/docker` now pass a per-invocation `CHECK_EPOCH` nonce, and the
`Dockerfile` (plus the Go multistage template in REPO_POLICIES.md, in both its
lint and builder stages) declares `ARG CHECK_EPOCH` with a guard that makes a
bare `docker build .` fail closed. Corrected the org-canonical text that
asserted a successful build implies all checks pass, across every document
carrying it: `REPO_POLICIES.md`, both repo checklists (which still told agents
to write the pre-fix `script/cibuild` and ended on an acceptance item the
guard makes unsatisfiable), and the Go styleguide.
- 2026-08-07: Set the canonical `.golangci.yml` to the org-standard v2-schema
config already deployed byte-identical across the org's Go repos (settings
under `linters.settings` so thresholds like lll/funlen/cyclop/dupl actually
apply under golangci-lint v2). Recorded the canonical golangci-lint version
(v2.12.2, commit-pinned) in REPO_POLICIES.md.
- 2026-03-20: Strengthened constructor naming and Params struct rules in the Go
styleguide.
- 2026-03-18: Documented fail-fast Dockerfile lint stage and conditional -v test
rerun patterns in REPO_POLICIES.md.
- 2026-03-11: Added HTTP service hardening policy for 1.0 releases.
- 2026-03-10: Added policy: no build artifacts in repos.
- 2026-03-04: Added LLM prose tells reference and copyediting checklist, then
several self-applied revision passes.
- 2026-02-28: Expanded the pre-1.0 schema migration rule; added clawpub
reference.
- 2026-02-23: Added Go style rules (no type-only packages, Stringer for
string-based types); template repos section in README.
- 2026-02-22: Initial policy corpus: REPO_POLICIES.md, code styleguides
(general, Go, JS, Python), repo checklists, CI policy, hash pinning, Go HTTP
server conventions, repo scaffolding.
# Future Steps
- Finish, format, and commit FIXUP_CLEAN.md and FIXUP_REPORT.md (the Next Step).
- Commit this TODO.md at the repo root; it is the last missing policy file.
- Decide the fate of untracked resume.sh: commit it or delete it.
- Add more prompt templates for common development tasks (from README TODO).

53
prompts/CODE_STYLEGUIDE_GO.md
View File

@@ -1,6 +1,6 @@
---
title: Code Styleguide — Go
last_modified: 2026-08-09
last_modified: 2026-02-22
---
1. Try to hard wrap long lines at 77 characters or less.
@@ -49,20 +49,7 @@ last_modified: 2026-08-09
```
```make
# ?= rather than := because this `$(shell git describe ...)` is only
# correct on the host. `.dockerignore` excludes `.git`, so evaluated
# inside a build stage it expands to the empty string without failing
# and the binary reports no version at all. The version is computed on
# the host by `script/docker` / `script/cibuild` and passed with
# `--build-arg VERSION=...`. If this repo's Dockerfile compiles by
# invoking make (`RUN make build`), `ARG VERSION` in that stage puts the
# value in the environment and `?=` defers to it. The canonical Go
# template in REPO_POLICIES.md instead runs `go build` directly with
# `-ldflags "... -X main.Version=${VERSION}"`, so there this Makefile is
# a host-only path — but it is still `?=`, because a repo that later
# moves the build behind make must not silently start shipping an empty
# version. See the git-describe rule in REPO_POLICIES.md.
VERSION ?= $(shell git describe --always --dirty)
VERSION := $(shell git describe --always --dirty)
BUILDARCH := $(shell uname -m)
GOLDFLAGS += -X main.Version=$(VERSION)
@@ -114,16 +101,9 @@ last_modified: 2026-08-09
`golangci-lint`.
1. Write a `Dockerfile` for every repo, even if it only runs the tests and
linting. `script/cibuild` and `script/docker` should always make sure that
the code is in an able-to-be-compiled state, linted, and any tests run, and
the build should fail if linting doesn't pass. That guarantee holds only
because those scripts pass a per-invocation `CHECK_EPOCH` build arg that
busts the check layers out of the Docker cache; without it an unchanged tree
serves those layers from cache and the build reports a green it never ran. A
bare `docker build .` fails closed by design, on the `[ -n "$CHECK_EPOCH" ]`
guard — always go through `script/cibuild` or `script/docker`. See
[Repository Policies](https://git.eeqj.de/sneak/prompts/raw/branch/main/prompts/REPO_POLICIES.md)
for the canonical form.
linting. `docker build .` should always make sure that the code is in an
able-to-be-compiled state, linted, and any tests run. The Docker build
should fail if linting doesn't pass.
1. Every repo must have a `Makefile`. See
[Repository Policies](https://git.eeqj.de/sneak/prompts/raw/branch/main/prompts/REPO_POLICIES.md)
@@ -156,15 +136,8 @@ last_modified: 2026-08-09
1. Provide a .gitignore file that ignores at least `*.log`, `*.out`, and
`*.test` files, as well as any binaries.
1. Constructors **must** be called `New()`. `modulename.New()` works great if
you name the packages properly. If the constructor creates an instance from
an existing value or representation, `From<Something>()` (e.g.
`FromBytes()`, `FromConfig()`) is also acceptable. If the package contains
multiple types and `New()` is ambiguous, `NewThing()` is occasionally
acceptable — but prefer restructuring packages so each type gets its own
package and a plain `New()`. Do not invent creative constructor names like
`Create()`, `Make()`, `Build()`, `Open()` (unless wrapping an OS resource),
or `Init()`. If you see a constructor with a non-standard name, rename it.
1. Constructors should be called `New()` whenever possible. `modulename.New()`
works great if you name the packages properly.
1. Don't make packages too big. Break them up.
@@ -176,15 +149,9 @@ last_modified: 2026-08-09
1. Use descriptive names for modules and filenames. Avoid generic names like
`server`. `util` is banned.
1. Constructors **must** take a `Params` struct (or `ThingParams` when
`NewThing()` is used), even for a single argument. Named fields in a Params
struct are always clearer than positional arguments. Positional arguments
for constructors are an endless source of bugs — they make call sites
unreadable, invite wrong-order errors that the compiler can't catch when
types coincide, and force every caller to update when a new field is added.
The only exception is when the single argument is stupidly obvious from
context — e.g. `featureflag.New(true)` or `thing.NewFromReader(r)`. When in
doubt, use a Params struct.
1. Constructors should take a Params struct if they need more than 1-2
arguments. Positional arguments are an endless source of bugs and should be
avoided whenever possible.
1. Use `context.Context` for all functions that need it. If you don't need it,
you can pass `context.Background()`. Anything long-running should get and

93
prompts/EXISTING_REPO_CHECKLIST.md
View File

@@ -1,6 +1,6 @@
---
title: Existing Repo Checklist
last_modified: 2026-08-09
last_modified: 2026-02-22
---
Use this checklist when beginning work in a repo that may not yet conform to our
@@ -24,57 +24,15 @@ with your task.
- [ ] `LICENSE` file exists and matches the README
- [ ] `REPO_POLICIES.md` exists and version date is current — fetch from
`https://git.eeqj.de/sneak/prompts/raw/branch/main/prompts/REPO_POLICIES.md`
- [ ] `.gitignore` is comprehensive (OS, editor, agent scratch, language
artifacts, secrets) — fetch from
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.gitignore` if missing.
An existing repo usually has a hand-written one that is never re-fetched,
so check the entries rather than the file's presence: `.claude/` in
particular, unanchored, so agent worktrees cannot be committed by
accident. Do not give it a `**/` prefix — that is a `.dockerignore` form
and is wrong here.
- [ ] `.gitignore` is comprehensive (OS, editor, language artifacts, secrets) —
fetch from `https://git.eeqj.de/sneak/prompts/raw/branch/main/.gitignore`
if missing
- [ ] `.editorconfig` exists — fetch from
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.editorconfig`
- [ ] `Dockerfile` and `.dockerignore` exist (fetch `.dockerignore` from
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.dockerignore`);
Dockerfile runs `make check` as a build step, and every stage containing a
check-running `RUN` declares `ARG CHECK_EPOCH` with the
`RUN [ -n "$CHECK_EPOCH" ] || exit 1` guard immediately below it — see the
`CHECK_EPOCH` rule in `REPO_POLICIES.md`. Without them the check layer is
served from cache on an unchanged tree and the build reports a green it
never ran.
- [ ] `.dockerignore` excludes the repo's own host-built artifacts (compiled
binaries, test binaries, coverage output), written root-anchored —
`/myapp`, never `**/myapp`, which would also match `cmd/myapp/`. An
existing repo is where such a binary is likeliest to already be sitting in
the build context, invisible to git.
- [ ] `.dockerignore` excludes `.claude`, root-anchored and with no `**/`
prefix. Agent worktrees are entire checkouts of the repo, so they inflate
the context by a multiple of it and can copy another session's unreviewed
work into an image layer. Confirm by enumerating the image, not by reading
the file — `.gitignore` hides these from `git status` too.
- [ ] **Do agents in this repo run anywhere other than the repo root?** The
scratch directory is created in the agent's working directory, so the
canonical anchored entry misses `services/api/.claude/` in a monorepo with
a per-service agent — it still reaches the build context and the image. An
existing repo is where such a layout already exists, so check it here
rather than assuming the canonical entry covers you: add anchored entries
for the subdirectories that have one (`/services/api/.claude`), or
`**/.claude` once you have confirmed no legitimately named nested
directory would be caught.
- [ ] If the repo embeds a version in a binary, that version is computed on the
host and passed with `--build-arg VERSION=...` by `script/docker` and
`script/cibuild`. No stage calls `git describe`: `.dockerignore` excludes
`.git`, so it yields an empty version without failing the build. A
tag-derived version additionally needs `fetch-depth: 0` on the CI checkout
step, which clones shallow and fetches no tags by default.
- [ ] Every depth-independent pattern in `.dockerignore` carries a `**/` prefix;
only genuinely root-anchored entries such as `.git` are unprefixed, and
`.gitignore`'s patterns have not been transplanted unmodified.
`.dockerignore` anchors an unprefixed pattern at the context root, so the
transplanted form leaves `config/.env` and `certs/server.key` in the build
context while reading as solved — see the `.dockerignore` rule in
`REPO_POLICIES.md`.
- [ ] Gitea Actions workflow in `.gitea/workflows/` runs `script/cibuild` on
- [ ] `Dockerfile` and `.dockerignore` exist; Dockerfile runs `make check` as a
build step — fetch `.dockerignore` from
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.dockerignore`
- [ ] Gitea Actions workflow in `.gitea/workflows/` runs `docker build .` on
push — reference
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.gitea/workflows/check.yml`
- [ ] Language-specific config:
@@ -87,26 +45,12 @@ with your task.
- [ ] Python: `pyproject.toml`
- [ ] Docs/writing: `.prettierrc`, `.prettierignore` (same URLs as above)
# Makefile and script/ Entrypoints
# Makefile
- [ ] `Makefile` exists in root — reference
`https://git.eeqj.de/sneak/prompts/raw/branch/main/Makefile`
- [ ] Has targets: `test`, `lint`, `fmt`, `fmt-check`, `check`, `docker`,
`hooks`
- [ ] Target implementations live in `script/` (scripts-to-rule-them-all);
Makefile targets are thin shims calling them — model scripts at
`https://git.eeqj.de/sneak/prompts/raw/branch/main/script/<name>`
- [ ] `script/precommit` exists and the pre-commit hook (installed by
`script/install-precommit`, shimmed by `make hooks`) runs it
- [ ] README has an **Entrypoints** section documenting the `script/`
entrypoints and linking the standard
- [ ] Go: `script/lint` isolates golangci-lint per checkout —
`GOLANGCI_LINT_CACHE` and `TMPDIR` both exported into `.lint-cache/`
(which is in `.gitignore` and `.dockerignore`), `--allow-serial-runners`
passed, and the lock error retried rather than reported as findings. Copy
the canonical block from `REPO_POLICIES.md`. Setting only the cache is the
common half-fix and leaves `parallel golangci-lint is running` failing
runs red.
- [ ] `make check` does not modify any files in the repo
- [ ] `make test` has a 30-second timeout
- [ ] `make test` runs real tests, not a no-op (at minimum, import/compile
@@ -134,25 +78,8 @@ with your task.
`internal/`, `static/`, etc.)
- [ ] Go migrations in `internal/db/migrations/` and embedded in binary
# HTTP Service Hardening (if targeting 1.0 and the repo is an HTTP/web service)
- [ ] Security headers set on all responses (HSTS, CSP, X-Frame-Options,
X-Content-Type-Options, Referrer-Policy, Permissions-Policy)
- [ ] Request body size limits enforced on all endpoints
- [ ] Read/write/idle timeouts configured on the HTTP server (slowloris defense)
- [ ] Per-handler execution time limits in place
- [ ] Password-based auth endpoints are rate-limited
- [ ] CSRF tokens on all state-mutating HTML forms
- [ ] Passwords hashed with bcrypt, scrypt, or argon2
- [ ] Session cookies use HttpOnly, Secure, and SameSite attributes
- [ ] True client IP correctly detected behind reverse proxy (trusted proxy
allowlist configured)
- [ ] CORS restricted to explicit origin allowlist for authenticated endpoints
- [ ] Error responses do not leak stack traces, SQL queries, or internal paths
# Final
- [ ] `make check` passes
- [ ] `script/cibuild` succeeds (a bare `docker build .` fails closed by design,
on the `CHECK_EPOCH` guard)
- [ ] `docker build` succeeds
- [ ] Commit and merge fixes before starting your actual task

11
prompts/GO_HTTP_SERVER_CONVENTIONS.md
View File

@@ -1,6 +1,6 @@
---
title: Go HTTP Server Conventions
last_modified: 2026-08-09
last_modified: 2026-02-22
---
This document defines the architectural patterns, design decisions, and
@@ -991,14 +991,7 @@ func main() {
Use ldflags to inject version information at build time:
```makefile
# ?= rather than := because this `$(shell git describe ...)` is only correct
# on the host: `.dockerignore` excludes `.git`, so evaluated inside a build
# stage it expands to the empty string without failing and the binary reports
# no version. The version is computed on the host by `script/docker` /
# `script/cibuild` and passed with `--build-arg VERSION=...`; where the build
# stage invokes make, `ARG VERSION` puts it in the environment and `?=` defers
# to it. See the git-describe rule in REPO_POLICIES.md.
VERSION ?= $(shell git describe --tags --always)
VERSION := $(shell git describe --tags --always)
BUILDARCH := $(shell go env GOARCH)
build:

318
prompts/LLM_PROSE_TELLS.md
View File

@@ -1,6 +1,9 @@
# LLM Prose Tells
A catalog of patterns found in LLM-generated prose.
All of these show up in human writing occasionally. No single one is conclusive
on its own. The difference is concentration — a person might lean on one or two
of these habits across an entire essay, but LLM output will use fifteen of them
per paragraph, consistently, throughout the entire piece.
---
@@ -13,11 +16,9 @@ A negation followed by an em-dash and a reframe.
> "It's not just a tool—it's a paradigm shift." "This isn't about
> technology—it's about trust."
### Em-Dash Overuse Generally
Even outside the "not X but Y" pivot, models substitute em-dashes for commas,
semicolons, parentheses, colons, and periods. The em-dash can replace any other
punctuation mark, so models default to it.
The single most recognizable LLM construction. Models produce this at roughly
10–50x the rate of human writers. Four of them in one essay and you know what
you're reading.
### The Colon Elaboration
@@ -25,25 +26,34 @@ A short declarative clause, then a colon, then a longer explanation.
> "The answer is simple: we need to rethink our approach from the ground up."
Models reach for this in every other paragraph. The construction is perfectly
normal; the frequency gives it away.
### The Triple Construction
> "It's fast, it's scalable, and it's open source."
Three parallel items in a list, usually escalating. Always exactly three (rarely
two, never four) with strict grammatical parallelism.
Three parallel items in a list, usually escalating. Always exactly three. Rarely
two. Never four. Strict grammatical parallelism that human writers rarely bother
maintaining.
### The Staccato Burst
> "This matters. It always has. And it always will." "The data is clear. The
> trend is undeniable. The conclusion is obvious."
Runs of very short sentences at the same cadence and matching length.
Runs of very short sentences at the same cadence. Human writers use a short
sentence for emphasis occasionally, but stacking three or four of them in a row
at matching length creates a mechanical regularity that reads as generated.
### The Two-Clause Compound Sentence
An independent clause, a comma, a conjunction ("and," "but," "which,"
"because"), and a second independent clause of similar length. Every sentence
becomes two balanced halves.
This might be the single most pervasive structural tell, and it's easy to miss
because each individual instance looks like normal English. The model produces
sentence after sentence in the same shape: an independent clause, a comma, a
conjunction ("and," "but," "which," "because"), and a second independent clause
of similar length. Over and over. Every sentence is two balanced halves joined
in the middle.
> "The construction itself is perfectly normal, which is why the frequency is
> what gives it away." "They contain zero information, and the actual point
@@ -53,62 +63,61 @@ becomes two balanced halves.
Human prose has sentences with one clause, sentences with three, sentences that
start with a subordinate clause before reaching the main one, sentences that
embed their complexity in the middle.
embed their complexity in the middle. When every sentence on the page has the
same two-part comma-conjunction-comma structure, the rhythm becomes monotonous
in a way that's hard to pinpoint but easy to feel.
### Uniform Sentences Per Paragraph
Model-generated paragraphs contain between three and five sentences, a count
that holds steady across a piece. If the first paragraph has four sentences,
every subsequent paragraph will too.
Model-generated paragraphs contain between three and five sentences, and this
count holds steady across an entire piece. If the first paragraph has four
sentences, every subsequent paragraph will too. Human writers are much more
varied — a single sentence followed by one that runs eight or nine — because
they follow the shape of an idea, not a template.
### The Dramatic Fragment
Sentence fragments used as standalone paragraphs for emphasis.
> "Full stop." "Let that sink in."
Sentence fragments used as standalone paragraphs for emphasis, like "Full stop."
or "Let that sink in." on their own line. Using one in an entire essay is a
reasonable stylistic choice, but models drop them in once per section or more,
at which point it stops being deliberate and becomes a habit.
### The Pivot Paragraph
> "But here's where it gets interesting." "Which raises an uncomfortable truth."
One-sentence paragraphs that exist only to transition between ideas, containing
zero information. The actual point is always in the next paragraph.
One-sentence paragraphs that exist only to transition between ideas. They
contain zero information. The actual point is always in the next paragraph.
Delete every one of these and the piece reads better.
### The Parenthetical Qualifier
> "This is, of course, a simplification." "There are, to be fair, exceptions."
Parenthetical asides inserted to perform nuance without changing the argument.
Parenthetical asides inserted to look thoughtful. The qualifier never changes
the argument that follows it. Its purpose is to perform nuance, not to express a
real reservation about what's being said.
### The Unnecessary Contrast
A contrasting clause appended to a statement that doesn't need one, using
"whereas," "as opposed to," "unlike," or "except that."
Models append a contrasting clause to statements that don't need one, tacking on
"whereas," "as opposed to," "unlike," or "except that" to draw a comparison the
reader could already infer.
> "Models write one register above where a human would, whereas human writers
> tend to match register to context."
The contrasting clause restates what the first clause already said. If you
delete the "whereas" clause and the sentence still says everything it needs to,
the contrast was filler.
### Unnecessary Elaboration
Models keep going after the sentence has already made its point.
> "A person might lean on one or two of these habits across an entire essay, but
> LLM output will use fifteen of them per paragraph, consistently, throughout
> the entire piece."
This sentence could end at "paragraph." The words after it repeat what "per
paragraph" already means. If you can cut the last third of a sentence without
losing meaning, the last third shouldn't be there.
The first clause already makes the point. The contrasting clause restates it
from the other direction. If you delete the "whereas" clause and the sentence
still says everything it needs to, the contrast was filler.
### The Question-Then-Answer
> "So what does this mean for the average user? It means everything."
A rhetorical question immediately followed by its own answer.
A rhetorical question immediately followed by its own answer. Models lean on
this two or three times per piece because it generates the feeling of forward
momentum without requiring any actual argument. A human writer might do it once.
---
@@ -116,38 +125,44 @@ A rhetorical question immediately followed by its own answer.
### Overused Intensifiers
"Crucial," "vital," "robust," "comprehensive," "fundamental," "arguably,"
The following words appear at dramatically elevated rates in model output:
"crucial," "vital," "robust," "comprehensive," "fundamental," "arguably,"
"straightforward," "noteworthy," "realm," "landscape," "leverage" (as a verb),
"delve," "tapestry," "multifaceted," "nuanced" (applied to the model's own
analysis), "pivotal," "unprecedented" (applied to things with plenty of
precedent), "navigate," "foster," "underscores," "resonates," "embark,"
"streamline," "spearhead."
"delve," "tapestry," "multifaceted," "nuanced" (which models apply to their own
analysis with startling regularity), "pivotal," "unprecedented" (frequently
applied to things with plenty of precedent), "navigate," "foster,"
"underscores," "resonates," "embark," "streamline," and "spearhead." Three or
more on the same page is a strong signal.
### Elevated Register Drift
Models write one register above where a human would, replacing "use" with
"utilize," "start" with "commence," "help" with "facilitate," "show" with
"demonstrate," "try" with "endeavor," "change" with "transform," and "make" with
"craft."
Models write one register above where a human would. "Use" becomes "utilize."
"Start" becomes "commence." "Help" becomes "facilitate." "Show" becomes
"demonstrate." "Try" becomes "endeavor." "Change" becomes "transform." "Make"
becomes "craft." The tendency holds regardless of topic or audience.
### Filler Adverbs
"Importantly," "essentially," "fundamentally," "ultimately," "inherently,"
"particularly," "increasingly." Dropped in to signal that something matters when
the writing itself should make the importance clear.
"particularly," "increasingly." Dropped in to signal that something matters,
which is unnecessary when the writing itself already makes the importance clear.
### The "Almost" Hedge
Instead of saying a pattern "always" or "never" does something, models write
"almost always," "almost never," "almost certainly," "almost exclusively." A
micro-hedge, less obvious than the full hedge stack.
Models rarely commit to an unqualified statement. Instead of saying a pattern
"always" or "never" does something, they write "almost always," "almost never,"
"almost certainly," "almost exclusively." The word "almost" shows up at
extraordinary density in model-generated analytical prose. It's a micro-hedge,
less obvious than the full hedge stack but just as diagnostic when it appears
ten or fifteen times in a single document.
### "In an era of..."
> "In an era of rapid technological change..."
Used to open an essay. The model is stalling while it figures out what the
actual argument is.
A model habit as an essay opener. The model uses it to stall while it figures
out what the actual argument is. Human writers don't begin a piece by zooming
out to the civilizational scale before they've said anything specific.
---
@@ -158,20 +173,25 @@ actual argument is.
> "While X has its drawbacks, it also offers significant benefits."
Every argument followed by a concession, every criticism softened. A direct
artifact of RLHF training, which penalizes strong stances.
artifact of RLHF training, which penalizes strong stances. The result is a model
that reflexively both-sides everything even when a clear position would serve
the reader better.
### The Throat-Clearing Opener
> "In today's rapidly evolving digital landscape, the question of data privacy
> has never been more important."
The first paragraph adds no information. Delete it and the piece improves.
The first paragraph of most model-generated essays adds no information. Delete
it and the piece improves immediately. The actual argument starts in paragraph
two.
### The False Conclusion
> "At the end of the day, what matters most is..." "Moving forward, we must..."
The high school "In conclusion,..." dressed up for a professional audience.
Signals that the model is wrapping up without actually landing on anything.
### The Sycophantic Frame
@@ -192,13 +212,15 @@ the key considerations:"
> cases it can potentially offer significant benefits."
Five hedges in one sentence ("worth noting," "while," "may not be," "in many
cases," "can potentially"), communicating nothing.
cases," "can potentially"), communicating nothing. The model would rather be
vague than risk being wrong about anything.
### The Empathy Performance
> "This can be a deeply challenging experience." "Your feelings are valid."
Generic emotional language that could apply to anything.
Generic emotional language that could apply equally to a bad day at work or a
natural disaster. That interchangeability is what makes it identifiable.
---
@@ -206,28 +228,34 @@ Generic emotional language that could apply to anything.
### Symmetrical Section Length
If the first section runs about 150 words, every subsequent section will fall
between 130 and 170.
If the first section of a model-generated essay runs about 150 words, every
subsequent section will fall between 130 and 170. Human writing is much more
uneven — 50 words in one section, 400 in the next.
### The Five-Paragraph Prison
Model essays follow a rigid introduction-body-conclusion arc even when nobody
asked for one. The introduction previews the argument, the body presents 3 to 5
points, the conclusion restates the thesis.
asked for one. Introduction previews the argument. Body presents 3–5 points.
Conclusion restates the thesis in different words.
### Connector Addiction
The first word of each paragraph forms an unbroken chain of transition words:
"However," "Furthermore," "Moreover," "Additionally," "That said," "To that
end," "With that in mind," "Building on this."
Look at the first word of each paragraph in model output. You'll find an
unbroken chain of transition words — "However," "Furthermore," "Moreover,"
"Additionally," "That said," "To that end," "With that in mind," "Building on
this." Human prose moves between ideas without announcing every transition.
### Absence of Mess
Model prose doesn't contradict itself mid-paragraph and then catch the
contradiction, go on a tangent and have to walk it back, use an obscure idiom
without explaining it, make a joke that risks falling flat, leave a thought
genuinely unfinished, or keep a sentence the writer liked the sound of even
though it doesn't quite work.
contradiction. It doesn't go on a tangent and have to walk it back, use an
obscure idiom without explaining it, make a joke that risks falling flat, leave
a thought genuinely unfinished, or keep a sentence the writer liked the sound of
even though it doesn't quite work.
Human writing does all of those things. The total absence of rough edges, false
starts, and odd rhythmic choices is one of the strongest signals that text was
machine-generated.
---
@@ -237,27 +265,45 @@ though it doesn't quite work.
> "This has implications far beyond just the tech industry."
Zooming out to claim broader significance without substantiating it.
Zooming out to claim broader significance without substantiating it. The model
has learned that essays are supposed to gesture at big ideas, so it gestures.
Nothing concrete is behind the gesture.
### "It's important to note that..."
This phrase and its variants ("it's worth noting," "it bears mentioning," "it
should be noted") function as verbal tics before a qualification the model
believes someone expects.
should be noted") appear at absurd rates in model output. They function as
verbal tics before a qualification the model believes someone expects.
### The Metaphor Crutch
Models rely on a small, predictable set of metaphors: "double-edged sword," "tip
of the iceberg," "north star," "building blocks," "elephant in the room,"
"perfect storm," "game-changer."
Models rely on a small, predictable set of metaphors — "double-edged sword,"
"tip of the iceberg," "north star," "building blocks," "elephant in the room,"
"perfect storm," "game-changer" — and reach for them with unusual regularity
across every topic. The pool is noticeably smaller than what human writers draw
from.
---
## How to Actually Spot It
No single pattern on this list proves anything by itself. Humans use em-dashes.
Humans write "crucial." Humans ask rhetorical questions.
What gives it away is how many of these show up at once. Model output will hit
10–20 of these patterns per page. Human writing might trigger 2–3, distributed
unevenly, mixed with idiosyncratic constructions no model would produce. When
every paragraph on the page reads like it came from the same careful, balanced,
slightly formal, structurally predictable process, it was probably generated by
one.
---
## Copyediting Checklist: Removing LLM Tells
Follow this checklist when editing any document to remove machine-generated
patterns. Do at least two full passes, because fixing one pattern often
introduces another.
patterns. Go through the entire list for every piece. Do at least two full
passes, because fixing one pattern often introduces another.
### Pass 1: Word-Level Cleanup
@@ -271,7 +317,8 @@ introduces another.
2. Search for filler adverbs ("importantly," "essentially," "fundamentally,"
"ultimately," "inherently," "particularly," "increasingly") and delete every
instance where the sentence still makes sense without it.
instance where the sentence still makes sense without it. That will be most
of them.
3. Look for elevated register drift ("utilize," "commence," "facilitate,"
"demonstrate," "endeavor," "transform," "craft" and similar) and replace with
@@ -279,6 +326,7 @@ introduces another.
4. Search for "it's important to note," "it's worth noting," "it bears
mentioning," and "it should be noted" and delete the phrase in every case.
The sentence that follows always stands on its own.
5. Search for the stock metaphors ("double-edged sword," "tip of the iceberg,"
"north star," "building blocks," "elephant in the room," "perfect storm,"
@@ -287,114 +335,91 @@ introduces another.
6. Search for "almost" used as a hedge ("almost always," "almost never," "almost
certainly," "almost exclusively") and decide in each case whether to commit
to the unqualified claim or to drop the sentence entirely.
7. Search for em-dashes and replace each one with the punctuation mark that
would normally be used in that position (comma, semicolon, colon, period, or
parentheses). If you can't identify which one it should be, the sentence
needs to be restructured.
8. Remove redundant adjectives. For each adjective, ask whether the sentence
changes meaning without it. "A single paragraph" means the same as "a
paragraph." "An entire essay" means the same as "an essay." If the adjective
doesn't change the meaning, cut it.
9. Remove unnecessary trailing clauses. Read the end of each sentence and ask
whether the last clause restates what the sentence already said. If so, end
the sentence earlier.
to the unqualified claim or to drop the sentence entirely. If the claim needs
"almost" to be true, it might not be worth making.
### Pass 2: Sentence-Level Restructuring
10. Find every em-dash pivot ("not X—but Y," "not just X—Y," "more than X—Y")
and rewrite it as two separate clauses or a single sentence that makes the
point without the negation-then-correction structure.
7. Find every em-dash pivot ("not X—but Y," "not just X—Y," "more than X—Y") and
rewrite it as two separate clauses or a single sentence that makes the point
without the negation-then-correction structure.
11. Find every colon elaboration and check whether it's doing real work. If the
8. Find every colon elaboration and check whether it's doing real work. If the
clause before the colon could be deleted without losing meaning, rewrite the
sentence to start with the substance that comes after the colon.
12. Find every triple construction (three parallel items in a row) and either
9. Find every triple construction (three parallel items in a row) and either
reduce it to two, expand it to four or more, or break the parallelism so the
items don't share the same grammatical structure.
13. Find every staccato burst (three or more short sentences in a row at similar
10. Find every staccato burst (three or more short sentences in a row at similar
length) and combine at least two of them into a longer sentence, or vary
their lengths so they don't land at the same cadence.
14. Find every unnecessary contrast ("whereas," "as opposed to," "unlike," "as
11. Find every unnecessary contrast ("whereas," "as opposed to," "unlike," "as
compared to," "except that") and check whether the contrasting clause adds
information not already obvious from the main clause. If the sentence says
the same thing twice from two directions, delete the contrast.
15. Check for the two-clause compound sentence pattern. If most sentences in a
passage follow the "\[clause\], \[conjunction\] \[clause\]" structure, first
try removing the conjunction and second clause entirely, since it's often
redundant. If the second clause does carry meaning, break it into its own
sentence, start the sentence with a subordinate clause, or embed a relative
clause in the middle instead of appending it at the end.
12. Check for the two-clause compound sentence pattern. If most sentences in a
passage follow the "[clause], [conjunction] [clause]" structure, rewrite
some of them. Break a few into two sentences. Start some with a subordinate
clause. Embed a relative clause in the middle of one instead of appending it
at the end. The goal is variety in sentence shape, not just sentence length.
16. Find every rhetorical question that is immediately followed by its own
13. Find every rhetorical question that is immediately followed by its own
answer and rewrite the passage as a direct statement.
17. Find every sentence fragment being used as its own paragraph and either
delete it or expand it into a complete sentence that adds information.
14. Find every sentence fragment being used as its own paragraph and either
delete it or expand it into a complete sentence that adds actual
information.
18. Check for unnecessary elaboration. Read every clause, phrase, and adjective
in each sentence and ask whether the sentence loses meaning without it. If
you can cut it and the sentence still says the same thing, cut it.
19. Check each pair of adjacent sentences to see if they can be merged into one
sentence cleanly. If a sentence just continues the thought of the previous
one, combine them using a participle, a relative clause, or by folding the
second into the first. Don't merge if the result would create a two-clause
compound.
20. Find every pivot paragraph ("But here's where it gets interesting." and
similar) and delete it.
15. Find every pivot paragraph ("But here's where it gets interesting." and
similar) and delete it. The paragraph after it always contains the actual
point.
### Pass 3: Paragraph and Section-Level Review
21. Review the last sentence of each paragraph. If it restates the point the
paragraph already made, delete it.
22. Check paragraph lengths across the piece and verify they actually vary. If
16. Check paragraph lengths across the piece and verify they actually vary. If
most paragraphs have between three and five sentences, rewrite some to be
one or two sentences and let others run to six or seven.
23. Check section lengths for suspicious uniformity. If every section is roughly
17. Check section lengths for suspicious uniformity. If every section is roughly
the same word count, combine some shorter ones or split a longer one
unevenly.
24. Check the first word of every paragraph for chains of connectors ("However,"
18. Check the first word of every paragraph for chains of connectors ("However,"
"Furthermore," "Moreover," "Additionally," "That said"). If more than two
transition words start consecutive paragraphs, rewrite those openings to
start with their subject.
25. Check whether every argument is followed by a concession or qualifier. If
19. Check whether every argument is followed by a concession or qualifier. If
the piece both-sides every point, pick a side on at least some of them and
cut the hedging.
26. Read the first paragraph and ask whether deleting it would improve the
20. Read the first paragraph and ask whether deleting it would improve the
piece. If it's scene-setting that previews the argument, delete it and start
with paragraph two.
27. Read the last paragraph and check whether it restates the thesis or uses a
21. Read the last paragraph and check whether it restates the thesis or uses a
phrase like "at the end of the day" or "moving forward." If so, either
delete it or rewrite it to say something the piece hasn't said yet.
### Pass 4: Overall Texture
28. Read the piece aloud and listen for passages that sound too smooth, too
22. Read the piece aloud and listen for passages that sound too smooth, too
even, or too predictable. Human prose has rough patches. If there aren't
any, the piece still reads as machine output.
29. Check that the piece contains at least a few constructions that feel
idiosyncratic: a sentence with unusual word order, a parenthetical that goes
on a bit long, an aside only loosely connected to the main point, a word
choice that's specific and unexpected.
23. Check that the piece contains at least a few constructions that feel
idiosyncratic — a sentence with unusual word order, a parenthetical that
goes on a bit long, an aside only loosely connected to the main point, a
word choice that's specific and unexpected. If every sentence is clean and
correct and unremarkable, it will still read as generated.
30. Verify that you haven't introduced new patterns while fixing the original
ones. Run the entire checklist again from the top on the revised version.
24. Verify that you haven't introduced new patterns while fixing the original
ones. This happens constantly. Run the entire checklist again from the top
on the revised version.
---
@@ -427,23 +452,18 @@ roughly like this:
> in common? _(pastes six sentences from the doc)_
>
> **model:** They're all exactly two independent clauses joined by a comma and a
> conjunction. Every single one is "\[statement\], \[conjunction\] \[second
> statement\]." The same sentence shape, over and over.
> conjunction. Every single one is "[statement], [conjunction] [second >
> statement]." The same sentence shape, over and over.
>
> **human:** the dramatic fragment paragraph has a tell in it
>
> **model:** "One of these in an entire essay is a stylistic choice. One per
> section is a tic." Two-clause parallel structure with the same shape, and also
> a staccato pair.
>
> **human:** add em dashes generally as a tell, and remove them all from the
> tells doc
>
> **model:** _(rewrites entire document without em-dashes while describing
> em-dash overuse)_
The human compared this process to the deleted scene in Terminator 2 where John
Connor switches the T-800's CPU to learning mode. The model compared it to a
physician trying to heal itself. Both are accurate.
physician trying to heal itself. Both descriptions are probably accurate.
This document has been through ten editing passes and it still has tells in it.
This document has been through six editing passes and it probably still has
tells in it.

107
prompts/NEW_REPO_CHECKLIST.md
View File

@@ -1,6 +1,6 @@
---
title: New Repo Checklist
last_modified: 2026-08-09
last_modified: 2026-02-22
---
Use this checklist when creating a new repository from scratch. Follow the steps
@@ -35,11 +35,7 @@ Template files can be fetched from:
- [ ] `.gitignore` — fetch from
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.gitignore`, extend for
language-specific artifacts. Extensions are written to `.gitignore`'s own
semantics, where an unanchored pattern already matches at every depth:
never add a `**/` prefix here, which is a `.dockerignore` form. The
canonical file already carries `.claude/` so agent worktrees cannot be
committed by accident.
language-specific artifacts
- [ ] `.editorconfig` — fetch from
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.editorconfig`
- [ ] `Makefile` — fetch from
@@ -56,34 +52,12 @@ Template files can be fetched from:
`https://git.eeqj.de/sneak/prompts/raw/branch/main/prompts/REPO_POLICIES.md`
- [ ] `Dockerfile` and `.dockerignore` — fetch `.dockerignore` from
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.dockerignore`
- Extend `.dockerignore` with the repo's own host-built artifacts, giving
every depth-independent pattern a `**/` prefix — but write a repo-root
binary anchored, `/myapp` and never `**/myapp`, which would also match
`cmd/myapp/` and delete the package directory. Do not transplant
`.gitignore`'s patterns: `.dockerignore` anchors an unprefixed pattern at
the context root, so the copied form leaves `config/.env` in the build
context while reading as solved. See the `.dockerignore` rule in
`REPO_POLICIES.md`. The canonical file's `.claude` entry is anchored for
the same reason as a repo-root binary; leave it that way, but note it only
covers agents running at the repo root — if this repo will run them in
subdirectories, `services/api/.claude/` is not excluded and needs its own
anchored entry.
- If the image embeds a version in a binary, the version is computed on the
host and passed with `--build-arg VERSION=...`. `ARG VERSION=dev` is
declared in the stage that compiles, and **no stage calls `git describe`**
— `.dockerignore` excludes `.git`, so it yields an empty version without
failing the build.
- All Dockerfiles must run `make check` as a build step, and every stage
containing a check-running `RUN` must declare `ARG CHECK_EPOCH` with the
`RUN [ -n "$CHECK_EPOCH" ] || exit 1` guard immediately below it — see the
`CHECK_EPOCH` rule in `REPO_POLICIES.md`. Without them the check layer is
served from cache on an unchanged tree and the build reports a green it
never ran.
- All Dockerfiles must run `make check` as a build step
- Server: also builds and runs the application
- Non-server: brings up dev environment and runs `make check`
- Image pinned by sha256 hash with version/date comment
- [ ] Gitea Actions workflow at `.gitea/workflows/check.yml` that runs
`script/cibuild` on push — reference
`docker build .` on push — reference
`https://git.eeqj.de/sneak/prompts/raw/branch/main/.gitea/workflows/check.yml`
- [ ] Language-specific:
- [ ] Go: `go mod init sneak.berlin/go/<name>`, `.golangci.yml` (fetch from
@@ -91,72 +65,15 @@ Template files can be fetched from:
- [ ] JS: `yarn init`, `yarn add --dev prettier`
- [ ] Python: `pyproject.toml`
## Configure script/ Entrypoints and Makefile
## Configure Makefile
Implementations live in `script/` (scripts-to-rule-them-all); Makefile targets
are thin shims calling them. Model scripts:
`https://git.eeqj.de/sneak/prompts/raw/branch/main/script/<name>`
- [ ] scripts are POSIX sh (`#!/bin/sh`, `set -eu`, no bashisms) so they run on
alpine images without bash
- [ ] `script/bootstrap` / `make bootstrap` — installs all dependencies,
idempotently, assuming nothing (pkg manager detection nix/apt/brew/apk;
node used if present, else pinned version via nvm from a hash-verified
archive; pinned yarn via corepack); Dockerfile runs it instead of inline
installs
- [ ] `script/setup` / `make setup` — readies a fresh clone: runs `bootstrap`,
then `install-precommit`, plus repo-specific init
- [ ] `script/test` / `make test` — runs real tests, not a no-op (30-second
timeout)
- [ ] `script/lint` / `make lint` — runs linter
- [ ] Go: exports `GOLANGCI_LINT_CACHE` **and** `TMPDIR` into a
`.lint-cache/` directory inside the checkout, above any
container-versus-host branch so every path that reaches the linter
gets them; passes `--allow-serial-runners` (never
`--allow-parallel-runners`); retries on
`parallel golangci-lint is running` detected on **stderr** and exits
75 with a VOID message on exhaustion. Copy the canonical block from
`REPO_POLICIES.md` rather than writing your own: a version that sets
only the cache leaves the false-red half live, and one that detects
the collision by exit status can retry a real finding away.
- [ ] Go: `.lint-cache/` is in both `.gitignore` and `.dockerignore`
- [ ] `script/fmt` / `make fmt` — formats code (writes)
- [ ] `script/fmt-check` / `make fmt-check` — checks formatting (read-only)
- [ ] `script/check` / `make check` — runs `test`, `lint`, `fmt-check`; must not
modify files
- [ ] `script/projectname` — outputs the project name (used by `script/docker`
for the image tag)
- [ ] `script/docker` / `make docker` — builds Docker image, tagged via
`script/projectname` (byte-identical across repos); carries the same three
version lines as `script/cibuild` below, and passes
`--build-arg CHECK_EPOCH="$epoch"` and `--build-arg VERSION="$version"`
- [ ] `script/cibuild` — cd to repo root, then, each on its own line:
```sh
epoch="$(date +%s%N)$$"
version="$(git describe --tags --always --dirty 2>/dev/null || true)"
[ -n "$version" ] || version="unknown"
docker build \
--build-arg CHECK_EPOCH="$epoch" \
--build-arg VERSION="$version" \
.
```
(what CI runs). Both build args are mandatory, and both assignments must be
on their own line: a failing command substitution inside an argument does
not trip `set -e`, so the inline form degrades silently to an empty
constant. The `[ -n "$version" ]` line is a live check that fires on an
export with no `.git` and on a repo with no commits — keep it, and do not
collapse it into `|| echo unknown`, which makes it unreachable. See the
`CHECK_EPOCH` and git-describe rules in `REPO_POLICIES.md` for why each
element is load-bearing. A bare `docker build .` fails closed by design.
- [ ] `script/precommit` — called by the pre-commit hook; runs `script/check`
- [ ] `script/install-precommit` — installs the pre-commit hook that runs
`script/precommit`
- [ ] `make hooks` — shims to `script/install-precommit`
- [ ] README **Entrypoints** section documents the scripts and links the
standard
- [ ] `make test` — runs real tests, not a no-op (30-second timeout)
- [ ] `make lint` — runs linter
- [ ] `make fmt` — formats code (writes)
- [ ] `make fmt-check` — checks formatting (read-only)
- [ ] `make check` — prereqs: `test`, `lint`, `fmt-check`; must not modify files
- [ ] `make docker` — builds Docker image
- [ ] `make hooks` — installs pre-commit hook
# 4. Verify

1027
prompts/REPO_POLICIES.md
View File

File diff suppressed because it is too large Load Diff

136
script/bootstrap
View File

@@ -1,136 +0,0 @@
#!/bin/sh
# script/bootstrap: install all dependencies needed to build and develop
# this repo. Idempotent: every install is guarded by a check so already
# installed tools are skipped. Base tooling comes from nix, apt, brew,
# or apk (detected in that order); assumes nothing is present. Node is
# used directly if installed; otherwise it is installed at a pinned
# version via nvm (installing nvm itself first, from a hash-verified
# release archive, never curl | sh).
set -eu
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
# Pinned versions, 2026-07-06
NODE_VERSION="22.17.0"
NVM_VERSION="0.40.3"
# sha256 of https://github.com/nvm-sh/nvm/archive/refs/tags/v0.40.3.tar.gz
NVM_SHA256="5f4d6aaa04a177dc93c985e31dbc411ab6b8c6e1e21d8015dbc1372625fcd1d0"
YARN_VERSION="1.22.22"
PKGMGR=""
SUDO=""
detect_pkgmgr() {
[ -n "$PKGMGR" ] && return 0
if command -v nix-env >/dev/null 2>&1; then
PKGMGR="nix"
elif command -v apt-get >/dev/null 2>&1; then
PKGMGR="apt"
elif command -v brew >/dev/null 2>&1; then
PKGMGR="brew"
elif command -v apk >/dev/null 2>&1; then
PKGMGR="apk"
else
echo "bootstrap: no supported package manager (nix, apt, brew, apk)" >&2
exit 1
fi
if [ "$PKGMGR" = "apt" ]; then
export DEBIAN_FRONTEND=noninteractive
if [ "$(id -u)" != "0" ]; then
SUDO="sudo"
fi
fi
}
# pkg_install <nix-attr> <apt-pkg> <brew-formula> <apk-pkg>
pkg_install() {
detect_pkgmgr
case "$PKGMGR" in
nix) nix-env -iA "nixpkgs.$1" ;;
apt) $SUDO env DEBIAN_FRONTEND=noninteractive apt-get install -y "$2" ;;
brew) brew install "$3" ;;
apk) apk add --no-cache "$4" ;;
esac
}
missing() {
! command -v "$1" >/dev/null 2>&1
}
# verify_sha256 <file> <expected-hash>
verify_sha256() {
if command -v sha256sum >/dev/null 2>&1; then
actual="$(sha256sum "$1" | cut -d' ' -f1)"
else
actual="$(shasum -a 256 "$1" | cut -d' ' -f1)"
fi
if [ "$actual" != "$2" ]; then
echo "bootstrap: sha256 mismatch for $1" >&2
echo " expected: $2" >&2
echo " actual: $actual" >&2
exit 1
fi
}
# nvm is a bash script; run a command in a bash with nvm loaded
nvm_sh() {
bash -c ". \"\$HOME/.nvm/nvm.sh\" && $*"
}
ensure_nvm() {
[ -s "$HOME/.nvm/nvm.sh" ] && return 0
# nvm prerequisites; nvm itself requires bash
if missing bash; then pkg_install bash bash bash bash; fi
if missing curl; then pkg_install curl curl curl curl; fi
if missing git; then pkg_install git git git git; fi
tmp="$(mktemp -d)"
curl -fsSL -o "$tmp/nvm.tar.gz" \
"https://github.com/nvm-sh/nvm/archive/refs/tags/v${NVM_VERSION}.tar.gz"
verify_sha256 "$tmp/nvm.tar.gz" "$NVM_SHA256"
mkdir -p "$HOME/.nvm"
tar -xzf "$tmp/nvm.tar.gz" -C "$HOME/.nvm" --strip-components=1
rm -rf "$tmp"
}
ensure_node() {
if ! missing node; then return 0; fi
ensure_nvm
nvm_sh "nvm install $NODE_VERSION"
}
ensure_yarn() {
if ! missing yarn; then return 0; fi
if ! missing corepack; then
corepack enable
corepack prepare "yarn@$YARN_VERSION" --activate
elif [ -s "$HOME/.nvm/nvm.sh" ]; then
nvm_sh "nvm use $NODE_VERSION >/dev/null && corepack enable && \
corepack prepare yarn@$YARN_VERSION --activate"
else
npm install -g "yarn@$YARN_VERSION"
fi
}
install_js_deps() {
if missing yarn && [ -s "$HOME/.nvm/nvm.sh" ]; then
nvm_sh "nvm use $NODE_VERSION >/dev/null && cd \"$ROOT\" && \
yarn install --frozen-lockfile"
else
yarn install --frozen-lockfile
fi
}
main() {
cd "$ROOT"
if missing make; then pkg_install gnumake make make make; fi
if missing git; then pkg_install git git git git; fi
ensure_node
ensure_yarn
install_js_deps
echo "bootstrap complete"
}
main "$@"

14
script/check
View File

@@ -1,14 +0,0 @@
#!/bin/sh
# script/check: run all checks (test, lint, fmt-check). Our own
# extension to scripts-to-rule-them-all. Must not modify any files.
set -eu
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
main() {
"$SCRIPT_DIR/test"
"$SCRIPT_DIR/lint"
"$SCRIPT_DIR/fmt-check"
}
main "$@"

33
script/cibuild
View File

@@ -1,33 +0,0 @@
#!/bin/sh
# script/cibuild: run the CI build. The Dockerfile runs script/check, but
# that only proves anything because CHECK_EPOCH is a fresh nonce on every
# invocation: without it Docker serves the check layer from cache on an
# unchanged tree and the build exits 0 without running the suite.
set -eu
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
main() {
cd "$ROOT"
# Assign on its own line: a failing command substitution inside an
# argument does not trip `set -e`, which would silently degrade the
# nonce to an empty constant. `$$` is required because busybox `date`
# drops %N without erroring.
epoch="$(date +%s%N)$$"
# VERSION must be computed here, on the host: .dockerignore excludes
# .git, so `git describe` cannot run in any build stage and fails
# quietly there rather than erroring. Same own-line discipline as the
# epoch. `|| true` keeps a failing describe from tripping `set -e`
# and leaves the value empty; the guard below is then the single
# place the fallback is applied, and it does fire — on an export with
# no .git, or a repo with no commits yet. `unknown` is visibly wrong
# in a binary in a way that an empty version is not.
version="$(git describe --tags --always --dirty 2>/dev/null || true)"
[ -n "$version" ] || version="unknown"
docker build \
--build-arg CHECK_EPOCH="$epoch" \
--build-arg VERSION="$version" \
.
}
main "$@"

35
script/docker
View File

@@ -1,35 +0,0 @@
#!/bin/sh
# script/docker: build the Docker image tagged with the project name.
# Identical in all repos; the tag comes from script/projectname. The
# Dockerfile's checks only actually run because CHECK_EPOCH is a fresh
# nonce on every invocation; without it a warm cache turns this into a
# green that proves nothing.
set -eu
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
main() {
cd "$ROOT"
# Assign on its own line: a failing command substitution inside an
# argument does not trip `set -e`, which would silently degrade the
# nonce to an empty constant. `$$` is required because busybox `date`
# drops %N without erroring.
epoch="$(date +%s%N)$$"
# VERSION must be computed here, on the host: .dockerignore excludes
# .git, so `git describe` cannot run in any build stage and fails
# quietly there rather than erroring. Same own-line discipline as the
# epoch. `|| true` keeps a failing describe from tripping `set -e`
# and leaves the value empty; the guard below is then the single
# place the fallback is applied, and it does fire — on an export with
# no .git, or a repo with no commits yet. `unknown` is visibly wrong
# in a binary in a way that an empty version is not.
version="$(git describe --tags --always --dirty 2>/dev/null || true)"
[ -n "$version" ] || version="unknown"
docker build \
--build-arg CHECK_EPOCH="$epoch" \
--build-arg VERSION="$version" \
-t "$("$SCRIPT_DIR/projectname")" .
}
main "$@"

12
script/fmt
View File

@@ -1,12 +0,0 @@
#!/bin/sh
# script/fmt: format all files (writes).
set -eu
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
main() {
cd "$ROOT"
yarn run prettier --write '**/*.md' --tab-width 4 --prose-wrap always
}
main "$@"

12
script/fmt-check
View File

@@ -1,12 +0,0 @@
#!/bin/sh
# script/fmt-check: check formatting (read-only).
set -eu
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
main() {
cd "$ROOT"
yarn run prettier --check '**/*.md' --tab-width 4 --prose-wrap always
}
main "$@"

16
script/install-precommit
View File

@@ -1,16 +0,0 @@
#!/bin/sh
# script/install-precommit: install the git pre-commit hook that runs
# script/precommit. Our own extension to scripts-to-rule-them-all.
set -eu
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
main() {
cd "$ROOT"
hook=".git/hooks/pre-commit"
printf '#!/bin/sh\nset -e\nscript/precommit\n' > .git/hooks/pre-commit
chmod +x .git/hooks/pre-commit
echo "pre-commit hook installed: runs script/precommit"
}
main "$@"

13
script/lint
View File

@@ -1,13 +0,0 @@
#!/bin/sh
# script/lint: run the linter.
set -eu
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
main() {
cd "$ROOT"
echo "Linting markdown files..."
yarn run prettier --check '**/*.md' --tab-width 4 --prose-wrap always
}
main "$@"

12
script/precommit
View File

@@ -1,12 +0,0 @@
#!/bin/sh
# script/precommit: run by the git pre-commit hook; fails the commit if
# checks fail. Our own extension to scripts-to-rule-them-all.
set -eu
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
main() {
"$SCRIPT_DIR/check"
}
main "$@"

12
script/projectname
View File

@@ -1,12 +0,0 @@
#!/bin/sh
# script/projectname: output the name of this project. Our own
# extension to scripts-to-rule-them-all. Other scripts that need the
# name (e.g. script/docker) call this, so they can stay identical
# across all repos.
set -eu
main() {
echo "prompts"
}
main "$@"

13
script/setup
View File

@@ -1,13 +0,0 @@
#!/bin/sh
# script/setup: set up the repo for development after a fresh clone:
# installs dependencies and the git pre-commit hook.
set -eu
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
main() {
"$SCRIPT_DIR/bootstrap"
"$SCRIPT_DIR/install-precommit"
}
main "$@"

12
script/test
View File

@@ -1,12 +0,0 @@
#!/bin/sh
# script/test: run the test suite.
set -eu
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
main() {
cd "$ROOT"
echo "No tests defined."
}
main "$@"