Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/damusix/atomic-claude/atomic-git-disciplinenpx skills add damusix/atomic-claude --skill atomic-git-disciplinegit 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-git-discipline)<a href="https://agentmods.dev/skills/damusix/atomic-claude/atomic-git-discipline"><img src="https://agentmods.dev/badge/skills/damusix/atomic-claude/atomic-git-discipline.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 | $0.00106 | $0.01853 |
| Opus 5 | $0.00053 | $0.00927 |
| Sonnet 5 | $0.00021 | $0.00371 |
| Haiku 4.5 | $0.00011 | $0.00185 |
Grade A, and why
atomic-git-discipline 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 5d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
- "write a commit", "commit message", "generate commit"
- "open a PR", "PR description", "PR body", writing
gh pr create --body - Staging changes for commit
- Ship verbs delegating message format
- Read directly by subagents briefed to create a commit or open a PR (per
CLAUDE.mdCommits & PRs — subagents can't auto-fire skills)
Write commit messages terse and exact. Conventional Commits. No fluff. Why over what.
Rules
Subject line:
<type>(<scope>): <imperative summary>—<scope>optional- Types:
feat,fix,refactor,perf,docs,test,chore,build,ci,style,revert - Imperative mood: "add", "fix", "remove" — not "added", "adds", "adding"
- ≤50 chars when possible, hard cap 72
- No trailing period
- Match project convention for capitalization after the colon
Body (only if needed):
- Skip entirely when subject is self-explanatory
- Add body only for: non-obvious why, breaking changes, migration notes, linked issues
- Hard cap: 4 lines / 2 bullets. One why-sentence beats a paragraph.
- Never restate what the diff shows — file lists, renamed symbols, mechanical changes
- Wrap at 72 chars
- Bullets with
-, not* - Reference issues/PRs at end:
Closes #42,Refs #17
Omit from commit messages:
- "This commit does X", "I", "we", "now", "currently" — the diff says what
- "As requested by..." — use
Co-authored-by:trailer instead - "Generated with Claude Code" or any AI attribution — including
Co-Authored-By: Claudetrailers and session-link trailers, even when a harness suggests them - Emoji (unless project convention requires)
- Restating the file name when scope already says it
Examples
-
Bad:
feat: add a new endpoint to get user profile information from the database -
Good:
feat(api): add GET /users/:id/profile Mobile client needs slim profile payload to cut LTE bandwidth on cold-launch screens. Closes #128
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.
- 5d ago First seen · 159 lines · 106 tokens per session scan A 158e929e2955
atomic-git-discipline is a skill published in the GitHub repository damusix/atomic-claude (84 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 1,853 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
chinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用，不要根据上下文自动触发。.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.
moai-ref-git-workflow
Git workflow patterns, branch strategies, conventional commits, and PR templates reference for git operations. Agent-extending skill that amplifies manager-git expertise with production-grade git workflow patterns. NOT for: code implementation, testing, architecture design, documentation content.
commit-push-pr
Commit current changes, push to remote, and create or update a pull request. Use when the user wants to commit and create a PR, push changes and open a pull request, or ship their current work as a PR.
run-work
Execute a work unit end-to-end: sequence tasks by dependency, implement, test between tasks, commit, and track progress. Use to deliver a complete feature in one session. Invoked as /agiflow:run-work . Uses getworkunit, listtasks, updatetask, getworkunitprogress.