commit-atomic

commit-atomic is a skill for Claude Code, Codex from jellydn/my-ai-tools. It costs 14 tokens per session (953 once invoked), scanned A, original, MIT.

A workflow for turning staged code changes into small, logically separate commits using the Commitizen or Conventional Commits style. A staged change is a change selected for inclusion in the next Git commit.

In plain words
What is it for?
Use it to inspect changes, group them by concern, stage files or selected parts intentionally, and create clear commits in dependency order.
Why use it?
It prevents unrelated edits from being bundled together and makes the project history easier to understand and review.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/jellydn/my-ai-tools/commit-atomic
Any agent
npx skills add jellydn/my-ai-tools --skill commit-atomic
Clone the repo
git clone --depth 1 https://github.com/jellydn/my-ai-tools

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 commit-atomic

README.md
[![agentmods](https://agentmods.dev/badge/skills/jellydn/my-ai-tools/commit-atomic.svg)](https://agentmods.dev/skills/jellydn/my-ai-tools/commit-atomic)
Your own site
<a href="https://agentmods.dev/skills/jellydn/my-ai-tools/commit-atomic"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/commit-atomic.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 953 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00953
Opus 5 $0.00007 $0.00477
Sonnet 5 $0.00003 $0.00191
Haiku 4.5 $0.00001 $0.00095

Measured 4d ago against content hash a03bf1fe180f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

commit-atomic 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 4d 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.

configs/amp/plugins/my-ai-tools-skills/skills/commit-atomic/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atomic Commit with Logical Grouping

Create atomic commits by logically grouping changes following the commitizen/conventional commits convention. Each commit should represent one logical change with a clear, informative message explaining the what and why.

Usage

/commit-atomic

Process

1. Inspect the current changes

git status
git diff --staged
git diff

Review all modified, added, and deleted files to understand the full scope of changes.

2. Group changes logically

Analyze the changes and group them into logical, independent units. Each group should:

  • Address a single concern or feature
  • Be independently understandable
  • Not break the build or tests on its own
  • Follow the dependency order (low-level to high-level)

Grouping strategies:

  • By feature or concern (e.g., authentication, UI, database)
  • By type (e.g., refactoring, bug fix, new feature)
  • By layer (e.g., model, service, controller)

3. Stage each group intentionally

Stage files explicitly with git add <path>. Avoid git add -A or git add --all:

# Stage specific files
git add <file1> <file2>

# Stage specific hunks interactively
git add -p <file>

# Verify what is staged before committing
git diff --staged

4. Commit each group with a commitizen message

Follow the commitizen conventional commits format:

<type>(<scope>): <subject>

[optional body]

[optional footer]

Types:

Type When to use
feat A new feature
fix A bug fix
docs Documentation only changes
style Formatting, missing semicolons (no code logic change)
refactor Code change that is neither a fix nor a feature
perf A code change that improves performance
test Adding or fixing tests
chore Build process or auxiliary tool changes
ci CI configuration changes
build Changes that affect the build system or dependencies
revert Reverts a previous commit

Read the full file on GitHub · 142 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. 4d ago First seen · 142 lines · 14 tokens per session scan A a03bf1fe180f

Subscribe to this mod's changes

commit-atomic is a skill published in the GitHub repository jellydn/my-ai-tools (119 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 953 once invoked, about $0.0001 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.