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 skills add paulinevos/claude-stuff --skill maintain-atomic-commitsgit clone --depth 1 https://github.com/paulinevos/claude-stuffWrote 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/paulinevos/claude-stuff/maintain-atomic-commits)<a href="https://agentmods.dev/skills/paulinevos/claude-stuff/maintain-atomic-commits"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/maintain-atomic-commits/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/paulinevos/claude-stuff/maintain-atomic-commits"><img src="https://agentmods.dev/badge/skills/paulinevos/claude-stuff/maintain-atomic-commits.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00253 | $0.01182 |
| Opus 5 | $0.00127 | $0.00591 |
| Sonnet 5 | $0.00051 | $0.00236 |
| Haiku 4.5 | $0.00025 | $0.00118 |
Grade A, and why
maintain-atomic-commits 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 10d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
maintain-atomic-commits
When a change belongs to a commit that already exists, fold it in rather than leaving a "fix typo" follow-up (see conventions for why). This skill picks the mechanism by where the change goes and when you made it.
First: which commit does the change belong to?
List what's still local and safe to rewrite with git log --oneline [base]..HEAD.
You MUST NOT rewrite a commit already on a shared branch (see
conventions).
Then route:
| Situation | Go to |
|---|---|
Belongs in the latest commit (HEAD) |
A — amend |
| Belongs in an older commit, and you haven't written the change yet | B — edit in place |
| Belongs in older commit(s), and you've already made the change (maybe spanning several commits) | C — fixup + autosquash |
If two situations seem to fit, prefer the simplest that applies: A over B over C.
A — amend the latest commit
Cheapest case: nothing is stacked on HEAD, so just absorb the change.
- Confirm it belongs in
HEAD, not earlier:git log --oneline -5,git show HEAD. - Stage it:
git add [paths](orgit add -pfor specific hunks). git commit --amend(reword if the change alters what the commit does;--no-editto keep the message). Rewording alone isgit commit --amendtoo.
B — edit an older commit in its own context
Use this when you want to author the change as if you were back at that commit — e.g. you need the working tree in that commit's state to run its tests, or the change is interdependent and awkward to isolate as a clean hunk later.
git rebase -i HEAD~[n](orgit rebase -i [base-branch]).- Change the target commit's prefix from
picktoe(edit); save. Git stops with that commit checked out. - Make and stage the change, then
git commit --amend(reword if needed). git rebase --continueto replay the rest. If replay conflicts, resolve it (seeresolve-merge-conflict) and continue.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 78 lines · 253 tokens per session scan A 3b85e0ed71d8
maintain-atomic-commits is a skill published in the GitHub repository paulinevos/claude-stuff (64 stars, last pushed yesterday), licensed MIT. It adds 253 tokens to every session and 1,182 once invoked, about $0.0013 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
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage repo-sync on macOS for shared documents and team context. Use when asked what repo-sync does, to automatically sync a repo, add a repo to repo-sync, stop syncing or un-sync a repo, check sync health, configure repo-sync, uninstall it, or install and maintain its bundled agent skill. Ordinary one-time Git pulls…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.