review-before-commit

A final review checklist for a completed development task before its results are saved or committed to Git.

In plain words
What is it for?
Use it to compare the code changes with the story, its acceptance criteria, and its verification steps before closing or committing the work.
Why use it?
It catches unnecessary changes, work outside the requested scope, and completion claims that cannot be verified.

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/usefulmove/enso/review-before-commit
Any agent
npx skills add usefulmove/enso --skill review-before-commit
Clone the repo
git clone --depth 1 https://github.com/usefulmove/enso

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 767 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 $0.00049 $0.00767
Opus 5 $0.00024 $0.00383
Sonnet 5 $0.00010 $0.00153
Haiku 4.5 $0.00005 $0.00077

Measured yesterday against content hash 53d32cfa3a2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-before-commit 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 yesterday.

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/review-before-commit/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to Use

Load this skill when:

  • A story's implementation is complete and you're about to move/close it
  • Before running git add/git commit at the end of a story
  • Before session-persist when code changes have been made
  • You want a final sanity check against behavioral drift

Invoke it explicitly. This is an advisory skill — it does not block execution.


Workflow

Step 1: Gather Evidence

  1. Read the active story document (the one in docs/stories/ you're closing)
  2. Run git diff to see what actually changed
  3. Review the story's Acceptance Criteria and Verification sections

Step 2: Check Principles

Run each check. If any fails, report the violation and suggest a fix.

§10.1 Think Before Coding — Did I plan?
  • The Approach section was filled out before execution started
  • No file modifications happened between "create story" and "complete approach"
  • Risks were identified upfront, not discovered during implementation
  • If failed: Reopen planning. Do not persist.
§10.2 Simplicity First — Is this the minimum?
  • No new abstractions were introduced for single-use code
  • No "flexibility" was added that wasn't explicitly requested
  • No features beyond the ask were implemented
  • If failed: List the speculative additions. Ask the user if they should stay.
§10.3 Surgical Changes — Did I touch only what I must?
  • No lines were changed that don't trace directly to the user's request
  • No adjacent code was "improved" (refactored, reformatted, commented)
  • Dead code created by MY changes was cleaned up
  • Pre-existing dead code was NOT removed unless explicitly asked
  • If failed: Revert unrelated changes, or flag them for user review.
§10.4 Goal-Driven Execution — Can I verify completion?
  • Every acceptance criterion has a checkmark or explicit reason why it's irrelevant
  • Verification steps (tests, builds, output checks) were run and passed
  • "Done" is not a gut feeling — it has evidence (passing tests, clean build, etc.)
  • If failed: Do not close the story. Run the missing verification steps.

Read the full file on GitHub · 87 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. yesterday First seen · 87 lines · 49 tokens per session scan A 53d32cfa3a2f

Subscribe to this mod's changes

review-before-commit is a skill published in the GitHub repository usefulmove/enso (2 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 767 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

harness-creator

Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…

walkinglabs/learn-harness-engineering · 142 tokens

harness

하네스를 구성합니다. 전문 에이전트를 정의하며, 해당 에이전트가 사용할 스킬을 생성하는 메타 스킬. (1) '하네스 구성해줘', '하네스 구축해줘' 요청 시, (2) '하네스 설계', '하네스 엔지니어링' 요청 시, (3) 새로운 도메인/프로젝트에 대한 하네스 기반 자동화 체계를 구축할 때, (4) 하네스 구성을 재구성하거나 확장할 때, (5) '하네스 점검', '하네스 감사', '하네스 현황', '에이전트/스킬 동기화' 등 기존 하네스 운영/유지보수 요청 시 사용.

revfactory/harness · 170 tokens

pr-review

Review a GitHub pull request and post a verdict comment. Stateful — if a previous review comment exists, review only the new commits since the last review and track whether prior findings were addressed. Focus on code cleanliness, duplication, and docs sync. Use when user says "review this PR", "check the PR", "leave…

lee-to/aif-handoff · 83 tokens

cc10x-router

THE ONLY ENTRY POINT FOR CC10X. Activate this skill for build, debug, review, and plan requests. Use when the user asks to implement, fix, review, plan, test, refactor, or continue code work. Trigger keywords: build, implement, create, write, add, review, audit, debug, fix, error, bug, broken, plan, design, architect…

romiluz13/cc10x · 125 tokens

new-plugin

Factory line for adding a new HAR verification plugin (like playwright or rocketsim) for any framework — research the framework docs, build the template under src/templates/plugins/, register it everywhere, validate on a real repository, and open a PR. Use when asked to add/create a plugin, plugin template, or…

os-factory/har · 89 tokens

factory-line

Factory line for executing one station of a declared multi-station program — read the installed line bundle (har line status), plan parallel work into isolated HAR slots, run the cumulative gate with har line gate, and hand off for human review. Use when asked to "run a factory line", "run the next station", "execute…

os-factory/har · 101 tokens