atomic-commits

A command that examines staged Git changes and organizes them into focused commits using Conventional Commits, a shared format for writing commit messages. It also checks related OpenSpec change documents when present.

In plain words
What is it for?
Use it when changes are staged to group them by purpose, account for related specifications, plan commit order, and apply the required commit prefixes.
Why use it?
It separates unrelated work into clearer commits, making the project history easier to understand and review.

Command for Claude Code

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 commands/spencermarx/open-code-review/atomic-commits
Clone the repo
git clone --depth 1 https://github.com/spencermarx/open-code-review

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 855 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 $0.00855
Opus 5 $0.00007 $0.00428
Sonnet 5 $0.00003 $0.00171
Haiku 4.5 $0.00001 $0.00085

Measured 3d ago against content hash 26f8353daec0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/atomic-commits.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atomic Commits

Analyze staged changes along with relevant requirements and OpenSpec files, then organize and commit them as intuitive atomic commits following conventional commits.

Prerequisites

  • Ensure there are staged changes (git diff --staged)
  • Review any related OpenSpec change documents in openspec/changes/

Steps

  1. Analyze Staged Changes

    • Run git diff --staged --name-only to list all staged files
    • Run git diff --staged to understand the actual changes
    • Group changes by logical concern (feature, fix, refactor, docs, spec, etc.)
  2. Identify Related OpenSpec Documents

    • Check if any staged changes relate to OpenSpec change documents in openspec/changes/
    • If OpenSpec files are staged, note which ones are non-archived (not in openspec/changes/archive/)
    • Read relevant OpenSpec documents to understand the context and requirements
  3. Plan Atomic Commits

    • Organize changes into logical, atomic commits that each represent a single cohesive change
    • Order commits in a sequence that makes sense (dependencies first, features second, cleanup last)
    • OpenSpec commits: Any commit related to OpenSpec documents should use the prefix spec: ...
    • Archive commit: If non-archived OpenSpec change documents are included, plan the final commit to archive them using openspec archive <id> --yes
  4. Execute Commits Sequentially

    • For each atomic commit: a. Unstage all files: git reset HEAD b. Stage only the files for this specific commit: git add <files> c. Commit with a conventional commit message: git commit -m "<type>(<scope>): <description>"
    • Conventional commit types: feat, fix, refact, doc, test, chore, style, perf, ci, build, spec
  5. Archive OpenSpec Changes (Final Commit)

    • If OpenSpec change documents were part of the staged changes and are non-archived:
      • Run openspec archive <id> --yes for each relevant change ID
      • Commit the archive with: git commit -m "spec: archive <change-id>"

Read the full file on GitHub · 80 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. 3d ago First seen · 80 lines · 14 tokens per session scan A 26f8353daec0

Subscribe to this mod's changes

atomic-commits is a command published in the GitHub repository spencermarx/open-code-review (351 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 855 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.