maintain-atomic-commits

maintain-atomic-commits is a skill for Claude Code from paulinevos/claude-stuff. It costs 253 tokens per session (1,182 once invoked), scanned A, original, MIT.

A set of Git instructions for keeping related changes together in one atomic commit, meaning a commit that represents one complete change. It chooses between amending the latest commit, editing an older local commit, or using fixup commits.

In plain words
What is it for?
Use it when a typo, tweak, or forgotten change belongs inside an existing local commit. It helps decide how to fold that change into the appropriate commit.
Why use it?
It prevents small corrections from being left as separate follow-up commits and helps keep local history easier to understand. It also warns against rewriting commits already shared with others.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the git-workflow plugin — 4 skills shipped together

Good fit Use it when a typo, tweak, or forgotten change belongs inside an existing local commit. It helps decide how to fold that change into the appropriate commit.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/paulinevos/claude-stuff/maintain-atomic-commits
Install

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.

Any agent
npx skills add paulinevos/claude-stuff --skill maintain-atomic-commits
Clone the repo
git clone --depth 1 https://github.com/paulinevos/claude-stuff

Made for: Claude Code.

Or install git-workflow, the plugin that ships this one along with the rest of its 4 skills.

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 maintain-atomic-commits

README.md
[![agentmods](https://agentmods.dev/badge/skills/paulinevos/claude-stuff/maintain-atomic-commits/github.svg)](https://agentmods.dev/skills/paulinevos/claude-stuff/maintain-atomic-commits)
Your own site
<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.

agentmods 80×15 button for maintain-atomic-commits

Your own site · 80×15
<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>
Per session 253 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,182 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00253 $0.01182
Opus 5 $0.00127 $0.00591
Sonnet 5 $0.00051 $0.00236
Haiku 4.5 $0.00025 $0.00118

Measured 10d ago against content hash 3b85e0ed71d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

plugins/git-workflow/skills/maintain-atomic-commits/SKILL.md · 78 lines

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.

  1. Confirm it belongs in HEAD, not earlier: git log --oneline -5, git show HEAD.
  2. Stage it: git add [paths] (or git add -p for specific hunks).
  3. git commit --amend (reword if the change alters what the commit does; --no-edit to keep the message). Rewording alone is git commit --amend too.

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.

  1. git rebase -i HEAD~[n] (or git rebase -i [base-branch]).
  2. Change the target commit's prefix from pick to e (edit); save. Git stops with that commit checked out.
  3. Make and stage the change, then git commit --amend (reword if needed).
  4. git rebase --continue to replay the rest. If replay conflicts, resolve it (see resolve-merge-conflict) and continue.

Read the full file on GitHub · 78 lines

Files

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.

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. 10d ago First seen · 78 lines · 253 tokens per session scan A 3b85e0ed71d8

Subscribe to this mod's changes

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.