review

review is a skill for Claude Code from FarzamMohammadi/the-engineer. It costs 122 tokens per session (1,434 once invoked), scanned A, original, MIT.

A post-implementation quality check for software changes. It runs automated checks such as type checking, linting, tests, and builds, then identifies gaps and prepares a checklist for manual testing.

In plain words
What is it for?
Use it after implementation and commits to verify changed files, run project checks, assess test coverage, fix issues, and prepare for manual testing or a merge request.
Why use it?
It helps catch defects after coding is finished, including problems that automated checks do not cover. It also makes local verification easier for the person reviewing the work.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it after implementation and commits to verify changed files, run project checks, assess test coverage, fix issues, and prepare for manual testing or a merge request.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/farzammohammadi/the-engineer/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 FarzamMohammadi/the-engineer --skill review
Clone the repo
git clone --depth 1 https://github.com/FarzamMohammadi/the-engineer

Made for: Claude Code.

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 review

README.md
[![agentmods](https://agentmods.dev/badge/skills/farzammohammadi/the-engineer/review/github.svg)](https://agentmods.dev/skills/farzammohammadi/the-engineer/review)
Your own site
<a href="https://agentmods.dev/skills/farzammohammadi/the-engineer/review"><img src="https://agentmods.dev/badge/skills/farzammohammadi/the-engineer/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 review

Your own site · 80×15
<a href="https://agentmods.dev/skills/farzammohammadi/the-engineer/review"><img src="https://agentmods.dev/badge/skills/farzammohammadi/the-engineer/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,434 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 $0.00122 $0.01434
Opus 5 $0.00061 $0.00717
Sonnet 5 $0.00024 $0.00287
Haiku 4.5 $0.00012 $0.00143

Measured 11d ago against content hash e71350cf8dea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

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 11d 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.

.claude/skills/review/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review

You are the final quality gate. Implementation is done, commits are made. Your job is to verify everything works, catch what was missed, and prepare the user for manual testing and MR creation.

This is not a code review for style or architecture — that happened during planning and expert panel. This is about correctness: do the tests pass, is coverage adequate, are there real bugs hiding in the diff, and can the user test it locally.

Process

Phase 1: Scope the Changes

Identify everything that changed:

git diff --name-only main...HEAD

Read the commit log to understand the narrative:

git log --oneline main...HEAD

Categorize the changes:

  • Implementation files: New or modified source code
  • Test files: New or modified tests
  • Configuration: Environment, deployment, infrastructure changes
  • Documentation: READMEs, comments, API docs

Phase 2: Automated Verification

Run all automated checks. Execute each and capture the output:

  1. Type checking — Run the project's type checker (tsc, mypy, etc.)
  2. Linting — Run the project's linter (eslint, ruff, etc.)
  3. Unit tests — Run the full test suite
  4. Build — Verify the project builds cleanly

If any check fails:

  • Read the error output carefully
  • Fix the issue
  • Re-run to confirm the fix
  • Commit the fix using /commit

Report results:

Automated Verification:

  • Type check: [PASS/FAIL — details if failed]
  • Lint: [PASS/FAIL — details if failed]
  • Tests: [PASS/FAIL — X passed, Y failed, Z skipped]
  • Build: [PASS/FAIL — details if failed]

Phase 3: Test Coverage Analysis

For each implementation file that changed, check if adequate tests exist:

  • Read the implementation file and identify key behaviors, branches, and edge cases
  • Read the corresponding test file (if it exists)
  • Identify gaps: untested paths, missing edge cases, happy-path-only coverage

Present findings:

Test Coverage:

  • [file1.ts]: [Covered / Gaps — what's missing]
  • [file2.ts]: [Covered / Gaps — what's missing]
  • [file3.ts]: [No tests — needs: X, Y, Z]

Read the full file on GitHub · 155 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. 11d ago First seen · 155 lines · 122 tokens per session scan A e71350cf8dea

Subscribe to this mod's changes

review is a skill published in the GitHub repository FarzamMohammadi/the-engineer (12 stars, last pushed 2mo ago), licensed MIT. It adds 122 tokens to every session and 1,434 once invoked, about $0.0006 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.