git-commit-review

git-commit-review is a skill for Claude Code, Codex from NickPolyder/NP.CoPilot.Config. It costs 39 tokens per session (3,792 once invoked), scanned A, original, MIT.

A short Git workflow for reviewing one logical set of staged changes before committing it. Git is a system for recording code changes, and a staged change is one selected for the next commit.

In plain words
What is it for?
Use it when a completed change is ready to commit. It checks the staged files, runs direct validations, performs a targeted review, and creates an approved commit.
Why use it?
It catches problems in the exact snapshot about to be saved. It also keeps commits focused and avoids committing unresolved serious findings.

Skill for Claude CodeCodex

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

Good fit Use it when a completed change is ready to commit. It checks the staged files, runs direct validations, performs a targeted review, and creates an approved commit.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nickpolyder/np.copilot.config/git-commit-review
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 NickPolyder/NP.CoPilot.Config --skill git-commit-review
Clone the repo
git clone --depth 1 https://github.com/NickPolyder/NP.CoPilot.Config

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 git-commit-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/nickpolyder/np.copilot.config/git-commit-review/github.svg)](https://agentmods.dev/skills/nickpolyder/np.copilot.config/git-commit-review)
Your own site
<a href="https://agentmods.dev/skills/nickpolyder/np.copilot.config/git-commit-review"><img src="https://agentmods.dev/badge/skills/nickpolyder/np.copilot.config/git-commit-review/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 git-commit-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/nickpolyder/np.copilot.config/git-commit-review"><img src="https://agentmods.dev/badge/skills/nickpolyder/np.copilot.config/git-commit-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,792 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 $0.00039 $0.03792
Opus 5.5 $0.00016 $0.01517
Sonnet 5.5 $0.00008 $0.00758
Haiku 4.5 $0.00004 $0.00379

Measured 1mo ago against content hash 8fc18d8242ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-commit-review 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 1mo 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/git-commit-review/SKILL.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Shared policy: Follow instructions/coordination.instructions.md for precedence, invocation, delegation, and handoffs; instructions/workflow.instructions.md for proportional verification; and instructions/git-conventions.instructions.md for delivery and commit safety.

This is the default pre-commit workflow. It is intentionally bounded to approximately ten minutes of reviewer time.

Use full-code-review only when the user explicitly requests exhaustive analysis. Recommendations for full-code-review or security-audit are separate handoffs after this owning workflow ends, never nested invocations. Never mark a blocked workflow complete merely to start another workflow.

When to use this skill

Use this skill when a logical change is ready to commit.

Do not use it for:

  • A user-requested full review, release candidate, major architectural change, security audit, or schema redesign; recommend full-code-review.
  • A trivial change when the user explicitly chooses to skip review.
  • An empty index.

1. Split atomic candidates and stage one

Inspect the worktree and divide it into logical, atomic commit candidates before adding reviewers.

  • Keep one feature, fix, refactor, configuration change, or documentation concern in each candidate.
  • Keep tests with the behavior they cover.
  • Do not compensate for a large mixed diff by adding reviewers.
  • Stage exactly one candidate with partial staging where necessary.
  • Confirm the index contains no unrelated files or hunks.

If a candidate is not self-contained, split it before continuing. Do not review unstaged changes or a mixture of candidates.

2. Materialize the clean index snapshot

Review the index, not the mutable worktree.

  1. Require a non-empty index diff against the recorded base: HEAD, or the empty tree for an unborn branch.
  2. Resolve $snapshotHelper to scripts\GitSnapshot.psm1 in this configuration's source repository, not the target project. The whole-repository installation provides it; do not assume a standalone copied skill includes it. If unavailable, stop and report the missing capability rather than inventing an archive fallback.
  3. Run the shared executable procedure below with $repositoryRoot identifying the target worktree root. New-GitReviewCandidate uses git write-tree only on a disposable index copy; it records the exact candidate tree, base identity, ordered parent list, unborn/detached/symbolic ref state, and destination ref. The snapshot and isolated child home are outside the target repository.

Read the full file on GitHub · 245 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. 1mo ago Changed · +27 lines 8fc18d8242ea
  2. 1mo ago First seen · 218 lines · 39 tokens per session scan A edaf4731b4e8

Subscribe to this mod's changes

git-commit-review is a skill published in the GitHub repository NickPolyder/NP.CoPilot.Config (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 3,792 once invoked, about $0.0002 per session on Opus 5.5. 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.