atomic-commits

atomic-commits is a skill for Claude Code, Codex from definite-d/agent-skills. It costs 100 tokens per session (678 once invoked), scanned A, original, MIT.

A workflow for turning a large set of uncommitted code changes into separate Git commits. Each commit contains one logical piece of work, such as infrastructure, a feature, integration, tests, or build files.

In plain words
What is it for?
Sorting changed files, choosing commit groups, checking existing commit-message conventions, and creating commits in dependency order.
Why use it?
It makes the project history easier to understand, review, and undo. It also orders commits so foundational changes come before code that depends on them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Sorting changed files, choosing commit groups, checking existing commit-message conventions, and creating commits in dependency order.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/definite-d/agent-skills/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 definite-d/agent-skills --skill atomic-commits
Clone the repo
git clone --depth 1 https://github.com/definite-d/agent-skills

Made for: Claude Code, Codex.

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-commits

README.md
[![agentmods](https://agentmods.dev/badge/skills/definite-d/agent-skills/atomic-commits.svg)](https://agentmods.dev/skills/definite-d/agent-skills/atomic-commits)
Your own site
<a href="https://agentmods.dev/skills/definite-d/agent-skills/atomic-commits"><img src="https://agentmods.dev/badge/skills/definite-d/agent-skills/atomic-commits.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 678 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 $0.00100 $0.00678
Opus 5 $0.00050 $0.00339
Sonnet 5 $0.00020 $0.00136
Haiku 4.5 $0.00010 $0.00068

Measured 8d ago against content hash 1464bd35ff0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 8d 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.

skills/atomic-commits/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atomic Commits Skill

Transform uncommitted changes into clean, logical commits using iterative analysis.

Workflow

1. Discover

git status
git diff --stat
git diff --name-only

2. Bucket by Functionality

Group files into logical buckets:

Bucket Use For Priority
Infrastructure Settings, constants, base classes 🔴 High
Feature/Refactor New capability, code restructure 🟡 Medium
Integration Routes, wiring, glue code 🟡 Medium
Tests Test files 🟢 Low
Build Generated files, lock files 🔵 Auto

3. Order by Dependency

  1. Infrastructure first (others depend on it)
  2. Feature/Refactor (core logic)
  3. Integration last (wiring it together)

4. Commit Each Bucket

For cleanly separated files:

git add path/to/bucket/files
git commit -m "type(scope): description"

For mixed changes in one file: Use granular-git skill.

Commit Messages

Follow Existing Patterns First

Check git log --oneline -20 for established conventions:

  • Scope names (e.g., backend, frontend, auth)
  • Type usage (e.g., feat, fix, refactor)
  • Message style

Fallback: Conventional Commits

<type>(<scope>): <description>
Type When
feat New feature
fix Bug fix
refactor Code restructure
chore Build, deps, tooling
test Tests only
style Formatting only
build Generated files

Description Rules

  1. Imperative mood: "add" not "added"
  2. 50 chars max
  3. Lowercase after scope
  4. No trailing period

Decision Checklist

Before each commit:

  • Changes are logically related
  • No unintended files
  • Dependencies satisfied
  • Message follows existing pattern

Merge Conflicts

When resolving, prefer the implementation that:

  1. Has better error handling
  2. Includes new features (Task, tracing)
  3. Follows updated patterns

See Also

Read the full file on GitHub · 106 lines

Files

What ships with it

3 files 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. 8d ago First seen · 106 lines · 100 tokens per session scan A 1464bd35ff0d

Subscribe to this mod's changes

atomic-commits is a skill published in the GitHub repository definite-d/agent-skills (2 stars, last pushed 6d ago), licensed MIT. It adds 100 tokens to every session and 678 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 2026-08-31.