code_review

A seven-step procedure for reviewing code changes. It requires checking the requested scope, changed files, automated quality checks, relevant documentation, and the final match against requirements.

In plain words
What is it for?
It is for reviewing a selected set of changes and producing a PASS or FAIL verdict with supporting details.
Why use it?
It gives code reviews a fixed checklist, making it less likely that tests, project context, or documentation differences are overlooked.

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/helmi/claude-simone/code_review
Clone the repo
git clone --depth 1 https://github.com/Helmi/claude-simone

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,270 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 $0.00000 $0.01270
Opus 5 $0.00000 $0.00635
Sonnet 5 $0.00000 $0.00254
Haiku 4.5 $0.00000 $0.00127

Measured 2d ago against content hash cfcd0b9abe5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code_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 2d 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:

legacy/.claude/commands/simone/code_review.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review - Execute top to bottom

Use the following instructions from top to bottom to execute a Code Review.

Create a TODO with EXACTLY these 7 Items

  1. Analyze the Scope given
  2. Find code changes within Scope
  3. Run automated quality checks (linting/type-checking)
  4. Find relevant Specification and Documentation
  5. Compare code changes against Documentation and Requirements
  6. Analyze possible differences
  7. Provide PASS/FAIL verdict with details

Follow step by step and adhere closely to the following instructions for each step.

DETAILS on every TODO item

1. Analyze the Scope given

check: <$ARGUMENTS>

If empty, use default, otherwise interpret <$ARGUMENTS> to identify the scope of the Review. Only continue if you can find meaningful changes to review.

CONTEXT: Before reviewing code changes:

  • Read .simone/00_PROJECT_MANIFEST.md to understand current sprint and milestone context
  • Use the manifest to identify which sprint is active and what work is in scope
  • Only evaluate against requirements appropriate for the current sprint's deliverables

2. Find code changes within Scope

With the identified Scope use git diff (on default: git diff HEAD~1) to find code changes.

3. Run automated quality checks (linting/type-checking)

Detect and run project's quality tools:

  1. Python projects:

    • If pyproject.toml with tool configs: Check for ruff, black, mypy, flake8, pylint
    • If .ruff.toml or ruff.toml: Run ruff check .
    • If setup.cfg or .flake8: Run flake8
    • Type checking: If mypy.ini or mypy in configs: Run mypy .
  2. JavaScript/TypeScript projects:

    • If package.json exists: Check "scripts" for "lint", "type-check", "format"
    • If .eslintrc* exists: Run appropriate eslint command
    • If tsconfig.json exists: Check for type-check script or run tsc --noEmit
    • If .prettierrc* exists: Check formatting
  3. Other languages:

    • Rust: If Cargo.toml: Run cargo fmt --check and cargo clippy
    • Go: If go.mod: Run go fmt ./... and go vet ./...
    • Ruby: If .rubocop.yml: Run rubocop
    • PHP: If phpcs.xml or .php-cs-fixer.php: Run appropriate tool

Read the full file on GitHub · 128 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. 2d ago First seen · 128 lines · 0 tokens per session scan A cfcd0b9abe5c

Subscribe to this mod's changes

code_review is a command published in the GitHub repository Helmi/claude-simone (558 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,270 tokens. 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.