atomic-claude: Skill for Claude Code

.claude/skills/atomic-release-ci/SKILL.md

atomic-release-ci is a skill for Claude Code from damusix/atomic-claude. It costs 96 tokens per session (3,246 once invoked), scanned A, original, MIT.

A project-specific guide for release-please, a tool that prepares release pull requests and version changes. It focuses on diagnosing failed CI checks for the release branch in this repository.

In plain words
What is it for?
Use it when release-please CI fails, the release branch is outdated, or the release pull request has the wrong changelog or a red check.
Why use it?
It helps distinguish routine release-branch problems from real code bugs. That gives maintainers a documented fix for recurring failures such as stale branches or incorrect changelogs.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths.

This is damusix/atomic-claude's own configuration. It tells Claude Code how to work on atomic-claude itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything atomic-claude configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/damusix/atomic-claude/main/.claude/skills/atomic-release-ci/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/damusix/atomic-claude

Made for: Claude Code.

Wrote 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.

agentmods badge for atomic-release-ci

README.md
[![agentmods](https://agentmods.dev/badge/skills/damusix/atomic-claude/atomic-release-ci.svg)](https://agentmods.dev/skills/damusix/atomic-claude/atomic-release-ci)
Your own site
<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>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,246 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash a9df3a4566d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

.claude/skills/atomic-release-ci/SKILL.md · 144 lines

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.ymlon: push: branches: [main]. Regenerates the release PR + branch. Uses secrets.RELEASE_PLEASE_TOKEN. No workflow_dispatch trigger, so the lever for a manual re-trigger is gh 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 testgo vetgofmtatomic 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.

Read the full file on GitHub · 144 lines

Changes

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.

  1. 7d ago First seen · 144 lines · 96 tokens per session scan A a9df3a4566d0

Subscribe to this mod's changes

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.

Related

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.

cwinvestments/memstack · 63 tokens

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.

alchemiststudiosDOTai/tunacode · 52 tokens

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.

epicsagas/epic-harness · 37 tokens

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…

axiomantic/spellbook · 134 tokens

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…

opencue/cuecards · 75 tokens

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?"…

yzonur/sap-adt-mcp · 131 tokens