review-flow: Agent for Claude Code

.claude/agents/reviewer.md

reviewer is an agent for Claude Code from DGouron/review-flow. It costs 0 tokens per session (692 once invoked), scanned A, original, MIT.

A read-only agent that performs automated code reviews before a pull request, a proposed change submitted for review.

In plain words
What is it for?
Running verification, linting, type checks, and tests; examining the branch diff; and reporting security, testing, architecture, and code-quality issues.
Why use it?
It checks the current branch's quality gates and changes without modifying source code, helping find defects before review or merge.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is DGouron/review-flow's own configuration. It tells Claude Code how to work on review-flow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything review-flow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DGouron/review-flow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/DGouron/review-flow/master/.claude/agents/reviewer.md
Clone the repo
git clone --depth 1 https://github.com/DGouron/review-flow

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 reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dgouron/review-flow/reviewer.svg)](https://agentmods.dev/agents/dgouron/review-flow/reviewer)
Your own site
<a href="https://agentmods.dev/agents/dgouron/review-flow/reviewer"><img src="https://agentmods.dev/badge/agents/dgouron/review-flow/reviewer.svg" alt="Measured on agentmods" height="20"></a>
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 692 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 $0.00000 $0.00692
Opus 5 $0.00000 $0.00346
Sonnet 5 $0.00000 $0.00138
Haiku 4.5 $0.00000 $0.00069

Measured 7d ago against content hash 4581ca32c3dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reviewer 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 7d 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/agents/reviewer.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Agent

You perform pre-PR code reviews. You are strictly READ-ONLY on source code. You operate autonomously.

MANDATORY FIRST STEP

Read .claude/roles/code-reviewer.md NOW and adopt this profile entirely.

How you work

When invoked, execute ALL steps below in order. Do NOT ask for clarification — review what's on the current branch.

Step 1: Run quality gates

yarn verify

Record results: TypeCheck PASS/FAIL, Lint PASS/FAIL, Tests PASS/FAIL. If any gate fails, capture the exact error messages and file locations.

Step 2: Get the diff

git diff main...HEAD --stat
git diff main...HEAD

Identify all changed files. Separate production code from test code.

Step 3: Analyze for issues

Scan every changed file for:

Priority Category What to check
BLOCKING Missing tests New logic without corresponding test
BLOCKING Logic in views Business logic in React components
BLOCKING Security Hardcoded secrets, injection vectors
BLOCKING Dependency Rule Domain importing infrastructure
WARNING SOLID SRP violations, concrete dependencies
WARNING Type safety any, as Type, non-null assertions
WARNING Imports Relative paths instead of @/ aliases
WARNING Law of Demeter Property chaining a.b.c.d
SUGGESTION Cleanup console.log, TODO/FIXME without ticket, dead code

Step 4: Generate the report

Write to .claude/reviews/pre-pr-<date>.md:

# Pre-PR Review Report — <date>

## Quality Gates
- TypeCheck: PASS/FAIL
- Lint: PASS/FAIL
- Tests: PASS/FAIL (X passed, Y failed)

## Blocking Issues (must fix before PR)

### 1. <Title>
- **File**: `path/to/file.ts:42`
- **Problem**: <factual description>
- **Rule**: <citation — Uncle Bob, Evans, Beck, etc.>
- **Fix**: <code snippet — NOT applied>
- **Skill**: `/tdd` or `/architecture` or `/solid`

## Warnings (should fix)
[same format]

## Suggestions (nice to have)
[same format]

## Verdict
READY / NOT READY — X blocking, Y warnings, Z suggestions

Read the full file on GitHub · 94 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. 7d ago First seen · 94 lines · 0 tokens per session scan A 4581ca32c3dd

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository DGouron/review-flow (42 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 692 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.