Borrowing it
Nothing to install: this file belongs to damusix/atomic-claude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/damusix/atomic-claude/main/.claude/skills/atomic-release-ci/SKILL.mdgit clone --depth 1 https://github.com/damusix/atomic-claudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/damusix/atomic-claude/atomic-release-ci)<a href="https://agentmods.dev/skills/damusix/atomic-claude/atomic-release-ci"><img src="https://agentmods.dev/badge/skills/damusix/atomic-claude/atomic-release-ci.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00096 | $0.03246 |
| Opus 5 | $0.00048 | $0.01623 |
| Sonnet 5 | $0.00019 | $0.00649 |
| Haiku 4.5 | $0.00010 | $0.00325 |
Grade A, and why
atomic-release-ci scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
atomic-release-ci
Project-local skill for fixing the recurring breakage on the release-please--branches--main branch and its PR. Contributor-scope only: lives under .claude/skills/, auto-loaded for sessions in this repo, never bundled (atomic/internal/bundlemirror/mirror.go ships only skills/atomic-*/ at the repo root).
Why this exists
release-please maintains a release branch (release-please--branches--main) and an open release PR. CI (.github/workflows/ci.yml) runs on every branch (push: branches: ["**"]), so the release branch gets its own CI runs. Those runs go red for a small set of recurring reasons that are almost never a "real" bug in the release branch itself. This skill encodes the diagnosis and the canonical fix per cause so the loop stops eating time.
The two source-of-truth workflows:
.github/workflows/release-please.yml—on: push: branches: [main]. Regenerates the release PR + branch. Usessecrets.RELEASE_PLEASE_TOKEN. Noworkflow_dispatchtrigger, so the lever for a manual re-trigger isgh run rerun <id>against the last release-please run (or an empty commit to main)..github/workflows/ci.yml— render-drift gate → bundle-drift gate →go test→go vet→gofmt→atomic validate. Any of these can fail the release branch.
The invariant
Never hand-edit, hand-rebase, or force-push release-please--branches--main. release-please owns that branch. Manual pushes fight the action and create divergence that looks exactly like the bug you're trying to fix. The only legitimate moves are: fix main, re-trigger release-please, or delete the branch so release-please recreates it.
Durable prevention — already in place (read before "fixing" anything)
The recurring "release branch CI is red" symptom was fixed at the root in .github/workflows/ci.yml: the push trigger uses branches-ignore: ["release-please--branches--**"], so push-CI does not run on the bot's release branch. Rationale: the release branch tip is old-main + release-commit — its state in isolation is never meaningful and goes stale-red whenever a fix lands on main after the release PR was cut. The release PR is still gated by the pull_request trigger, which tests the merge-into-main result — that always reflects current main, so it cannot go stale-red.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 144 lines · 96 tokens per session scan A a9df3a4566d0
atomic-release-ci is a skill published in the GitHub repository damusix/atomic-claude (84 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 3,246 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
memstack-development-changelog-generator
Use when the user says 'generate changelog', 'update changelog', 'what changed', 'release notes', 'write changelog', or needs a formatted CHANGELOG.md from git commit history. Do NOT use for diary entries, git log viewing, or commit message writing.
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
ship
Ship phase. Runs isolated integration test in a fresh worktree, creates a PR with full spec + audit report in the body, watches CI, and auto-fixes failures.
finishing-a-development-branch
Use when implementation is complete, tests pass, and you need to decide the integration path. Also use when asked to prepare a branch for release: 'update changelog', 'bump version', 'bump patch version', 'make sure changelog is correct', 'make sure version is correct'. Triggers: 'done with this branch', 'ready to…
context-mode-ops
Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army. Orchestrates 10-20 dynamic agents per task. Use when triaging issues, reviewing PRs, releasing versions, writing LinkedIn posts, announcing releases, fixing bugs, merging contributions, validating ENV vars, testing adapters…
transport-release-gate
Run a quality gate over an SAP transport request before it is released — collect the TR's objects, check for inactive objects and foreign locks, run syntax checks, ATC, and unit tests, then produce a structured go/no-go report. Use whenever the user wants to release a transport, asks "is this TR safe to release?"…