The canonical .dockerignore and .gitignore both omitted the in-repo agent scratch directory. On this fleet that directory holds one worktree per in-flight agent -- an entire additional checkout of the repo each -- so under `COPY . .` all of it reached the build context and the image. Measured on this repo before the change: five planted scratch files, at every depth beneath the directory, all present inside a probe image built from the real context. Three consequences, only the first of which is about size. The context inflates by a multiple of the repo. Another session's unreviewed and sometimes uncommitted work is copied into a build artifact. And the directory is created and destroyed constantly by tooling, so it invalidates `COPY . .` for reasons that have nothing to do with this repo's content -- which is the accidental cache protection described at length in the issue thread, and the reason this change was sequenced behind the CHECK_EPOCH bust rather than landed alongside the rest of the .dockerignore work. The two entries are deliberately different shapes, because the two files have different semantics and neither is derived from the other. In .dockerignore the entry is anchored, `.claude`, with no `**/` prefix: the directory occurs exactly once, at the context root, and the prefixed form additionally matches any nested directory of that name. Measured rather than argued -- the `**/`-prefixed control was built and enumerated too, and it removes prompts/.claude/ from the context as well, which in a repo with a legitimately named nested directory would silently delete it from the build. In .gitignore the entry is unanchored, `.claude/`, because a .gitignore pattern already matches at every depth; `git check-ignore -v` confirms it covering both .claude/ and prompts/.claude/, so a `**/` prefix there would be redundant at best, and on an anchored pattern it would be actively wrong. It is not case-folded the way the neighbouring secret patterns are. Tooling creates the directory in exactly one spelling, and a miss costs context bloat rather than exposure, so the character-class treatment that the secret names require would be noise here. The file says so, since the header comment is the only part of this guidance a consuming repo actually receives. The second half of this change is the consequence that ships broken silently. Excluding .git means `git describe` cannot run in any build stage, and it fails quietly there rather than erroring: `-X main.Version=` comes out empty, the binary reports no version, and the build still exits 0. The Go template in REPO_POLICIES.md had `ARG VERSION=dev` and never said where VERSION came from, which is precisely the gap a reader fills in with `git describe` inside the build. It now says: computed on the host, threaded in with `--build-arg VERSION=...`, shown as a complete command rather than as two rules each documenting half of one. script/docker and script/cibuild do it, with the same discipline the epoch already has -- assignment on its own line, because a failing command substitution inside an argument does not trip `set -e`, plus a non-empty fallback so a build from an export with no .git reports `unknown` rather than an empty string that reads as a successful version. The scripts pass VERSION unconditionally rather than growing a per-repo variant. This repo's Dockerfile declares no `ARG VERSION`, and BuildKit was measured accepting the unconsumed arg silently -- no warning, no cache effect, confirmed by the paired runs below in which the bootstrap layer still caches. The alternative, leaving it to each repo, reintroduces the trap: a repo that needs a version and finds no VERSION in its scripts writes `git describe` into the Dockerfile, which is the failure being closed. The same correction reaches the two Go documents that carry the GOLDFLAGS pattern, since a `$(shell git describe)` evaluated inside a build stage is exactly this empty version. Both are now `?=`, so an `ARG VERSION` in the compiling stage arrives through the environment and wins. Leaving them as `:=` would have left the corpus telling a reader one thing in the policy and the opposite in the styleguide. Both repo checklists gain the entries too. They are what an agent reads while writing these files, so they are where the wrong shape actually gets written: the .gitignore item is the one an existing repo never re-fetches, and it now names `.claude/` explicitly along with the warning not to prefix it. Verification, by enumerating a probe image rather than by reading the patterns. Standalone minimal Dockerfile held outside the context, `--no-cache` scoped to that one image, no prune of any kind. Before: all five planted scratch files in the image, 42 files total. After: zero, 37 files total, with README.md, script/check, prompts/NEW_REPO_CHECKLIST.md and a planted probe_src/app.md all still present as positive controls, so the exclusion is a real exclusion and not a COPY that stopped copying. Transferred context fell from 161.86kB to 68.82kB, recorded as corroboration only: BuildKit reports a delta, not a total, and an earlier run in this repo transferred 2.18kB while shipping 43 files. The CHECK_EPOCH verification was re-run under the changed context, because the context moved underneath the earlier measurement. Two consecutive script/cibuild runs on an unchanged tree: run 1 in 17.07s, run 2 in 5.73s, both executing the check layer with a distinct epoch and real prettier output from both lint and fmt-check. The `RUN script/bootstrap` layer is CACHED in run 2, which is the validity control -- it proves no concurrent prune landed between the runs and that no --no-cache path was taken, so the check layer executing is the bust working rather than a cold cache. Planted files were removed afterwards and their absence confirmed against the filesystem with `find`, not against `git status`, which cannot see them once .gitignore covers the directory -- the same blind spot that made the earlier secret exposure invisible.
prompts
prompts is an MIT-licensed collection of LLM prompts by @sneak, including development policy prompts and other useful prompts for working with large language models.
Quick Start
Existing Repo
Run from within the repo you want to bring up to standards. Clone the prompts repo once, then run both commands in order.
export TD="$(mktemp -d)"
git clone --depth 1 https://git.eeqj.de/sneak/prompts.git "$TD"
Repository structure and policies:
claude "Read $TD/prompts/REPO_POLICIES.md and
$TD/prompts/EXISTING_REPO_CHECKLIST.md, then bring this repo up to those
standards. Your scope is repo scaffolding and policy compliance:
Makefile, Dockerfile, .dockerignore, .gitignore, .editorconfig, CI
workflow, README sections, LICENSE, REPO_POLICIES.md, and any
language-specific config files (.golangci.yml, .prettierrc, etc.).
You must also run the formatter (make fmt) and fix any linter errors
(make lint) so that make check passes — this will touch source code,
but do not restructure, refactor, or rewrite any application logic.
Follow the policies yourself: work on a feature branch, never git add -A,
and make each logical change a separate commit (e.g. one commit for
formatting, one for linter fixes, one for README updates, one for each
new repo file added, etc.)."
Code style and conventions:
claude "Read $TD/prompts/CODE_STYLEGUIDE.md and whichever
language-specific styleguides in $TD/prompts/ apply to this repo
(CODE_STYLEGUIDE_GO.md, CODE_STYLEGUIDE_JS.md, CODE_STYLEGUIDE_PYTHON.md,
GO_HTTP_SERVER_CONVENTIONS.md). Then review the application code in this
repo and bring it into compliance with those coding standards. Your scope
is application code structure and style: naming, patterns, error
handling, project layout, and conventions described in the styleguides.
Do not modify repo scaffolding (Makefile, Dockerfile, CI workflow,
.gitignore, .editorconfig, etc.) — only application code. Work on a
feature branch, never git add -A, and make each logical change a
separate commit."
New Repo
Run from inside the directory where you want to create a new repo. Clone the prompts repo once, then run both commands in order.
export TD="$(mktemp -d)"
git clone --depth 1 https://git.eeqj.de/sneak/prompts.git "$TD"
Repository scaffolding:
claude "Read $TD/prompts/REPO_POLICIES.md and
$TD/prompts/NEW_REPO_CHECKLIST.md, then set up this new repo according
to those standards. Your scope is repo structure and required files:
README.md, LICENSE, REPO_POLICIES.md, Makefile, Dockerfile, .dockerignore,
.gitignore, .editorconfig, CI workflow, and language-specific config.
Run the formatter (make fmt) and fix any linter errors (make lint) so
that make check passes — this will touch source code, but do not
restructure, refactor, or rewrite any application logic. Follow the
policies yourself: work on a feature branch, never git add -A, and make
each logical change a separate commit (e.g. one commit for formatting,
one for linter fixes, one for README, one for each new repo file, etc.)."
Code style and conventions:
claude "Read $TD/prompts/CODE_STYLEGUIDE.md and whichever
language-specific styleguides in $TD/prompts/ apply to this repo
(CODE_STYLEGUIDE_GO.md, CODE_STYLEGUIDE_JS.md, CODE_STYLEGUIDE_PYTHON.md,
GO_HTTP_SERVER_CONVENTIONS.md). Then review the application code in this
repo and bring it into compliance with those coding standards. Your scope
is application code structure and style: naming, patterns, error
handling, project layout, and conventions described in the styleguides.
Do not modify repo scaffolding (Makefile, Dockerfile, CI workflow,
.gitignore, .editorconfig, etc.) — only application code. Work on a
feature branch, never git add -A, and make each logical change a
separate commit."
Getting Started
git clone https://git.eeqj.de/sneak/prompts.git
cd prompts
Prompts are stored as Markdown files in prompts/. Copy or reference them as
needed in your projects.
Entrypoints
This repository adheres to the
Scripts to Rule Them All
standard: normalized scripts in script/ are the entrypoints for the
development workflow, and the Makefile targets are thin shims that call them.
The scripts are POSIX sh (not bash) so they run in minimal containers such as
alpine. We provide:
script/bootstrap— install all dependencies (yarn install)script/setup— set up the repo for development after a fresh clone: runsscript/bootstrap, thenscript/install-precommitscript/projectname— output the project name (our own extension); used byscript/dockerfor the image tagscript/test— run the test suite (no tests defined here)script/lint— lint the markdown files with prettierscript/fmt— format all markdown files with prettier (writes)script/fmt-check— check formatting (read-only)script/check— run all checks:test,lint,fmt-check(our own extension)script/docker— build the Docker image, tagged viascript/projectname(byte-identical across repos); passes the sameCHECK_EPOCHnonce asscript/cibuildscript/cibuild— cd to the repo root, assignepoch="$(date +%s%N)$$", thendocker build --build-arg CHECK_EPOCH="$epoch" .(what CI runs; the image build runsscript/check, and the per-invocationCHECK_EPOCHnonce is what stops Docker serving that check from cache on an unchanged tree — a baredocker build .fails closed on purpose)script/precommit— run by the git pre-commit hook (our own extension); callsscript/checkscript/install-precommit— installs the git pre-commit hook (our own extension);make hooksshims 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 single authoritative source. This repo provides a central place to maintain, share, and evolve prompts across projects.
Design
The repository is a collection of Markdown files organized in the prompts/
subdirectory. Each file contains one or more related prompts or policy
documents. There is no build step or runtime component; the prompts are consumed
by copying them into other projects or referencing them directly.
Template Repos
These template repositories implement the policies defined in this repo and serve as starting points for new projects. They must be kept in sync when policies change.
- template-app-go — Go HTTP server template (Uber fx, chi, SQLite, session auth, Prometheus metrics)
- template-app-js — JavaScript SPA template (Vite, Tailwind CSS v4, nginx Docker deployment)
- template-app-python — Python web application template (FastAPI, uvicorn, pytest, black, ruff)
When updating policies in this repo, also update the template repos to match (Makefile targets, Dockerfile conventions, CI workflows, required files, etc.).
See Also
- clawpub — Real-world examples, rationale, and operational lessons from applying these policies with an OpenClaw AI agent. Includes detailed documentation on how the interlocking check system (CI → Docker → Makefile → tests/lint/fmt) works in practice, why checklists complement prose policies, and failure stories from production use.
TODO
- Add more prompt templates for common development tasks
License
MIT. See LICENSE.