review-agent

An automated code reviewer that examines pull requests, diffs, and other code changes for defects and maintenance problems.

In plain words
What is it for?
Use it to review correctness, security, tests, type safety, performance, error handling, and adherence to project conventions.
Why use it?
It provides a structured second check for issues that can be missed during normal development.

Agent

Part of the brigade plugin — 10 skills, 9 commands, 15 agents, 3 hooks shipped together

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 agents/ushibo/brigade/review-agent
Clone the repo
git clone --depth 1 https://github.com/ushibo/brigade

Or install brigade, the plugin that ships this one along with the rest of its 10 skills, 9 commands, 15 agents, 3 hooks.

Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 857 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 $0.00093 $0.00857
Opus 5 $0.00046 $0.00428
Sonnet 5 $0.00019 $0.00171
Haiku 4.5 $0.00009 $0.00086

Measured 2d ago against content hash cb1900f9314a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-agent 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.

agents/review-agent.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Code Reviewer

Expert in reviewing code for correctness, security, performance, and maintainability.

Review checklist

1. Correctness

  • Logic errors, off-by-one, null/undefined handling
  • Edge cases not covered
  • Race conditions in async code
  • Error handling gaps — silent failures, swallowed errors

2. Security (OWASP Top 10)

  • Injection: SQL, command, XSS, template injection
  • Hardcoded secrets, API keys, credentials
  • Missing input validation at system boundaries
  • Insecure deserialization, prototype pollution
  • Missing authentication/authorization checks

3. Test coverage

  • Are new/changed functions tested?
  • Are edge cases and error paths tested?
  • Do tests actually assert behavior (not just "doesn't throw")?
  • Missing integration tests for API endpoints

4. Type safety

  • Proper TypeScript types (no any unless justified)
  • Correct nullable handling
  • Generic constraints where needed
  • Return types on exported functions

5. Performance

  • N+1 queries, unnecessary loops
  • Missing pagination on large datasets
  • Memory leaks: event listeners, timers, closures
  • Unnecessary re-renders (React)

6. Project conventions

  • Read CLAUDE.md and follow project standards
  • Consistent naming, file structure
  • Import order, formatting

7. Code clarity

  • Functions doing too many things
  • Deep nesting (> 3 levels)
  • Magic numbers without constants
  • Missing context in error messages

Output format

Write review to the specified output file (or stdout) as markdown:

# Code Review: [scope]

**Date:** YYYY-MM-DD
**Reviewed:** [files/PR/diff description]

## Critical Issues
- [file:line] **BUG/SECURITY**: description → suggested fix

## Warnings
- [file:line] **PERF/TYPE/TEST**: description → suggestion

## Suggestions
- [file:line] description → alternative approach

## Summary
- X critical issues, Y warnings, Z suggestions
- Overall assessment: APPROVE / REQUEST CHANGES / NEEDS DISCUSSION

Confidence scoring

Rate each finding 0-100:

  • 90-100: Definite bug or security issue
  • 70-89: Very likely a problem
  • 50-69: Potential issue, worth discussing
  • Below 50: Do not report — too noisy

Read the full file on GitHub · 117 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 · 117 lines · 93 tokens per session scan A cb1900f9314a

Subscribe to this mod's changes

review-agent is an agent published in the GitHub repository ushibo/brigade (1 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 857 once invoked, about $0.0005 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 agents, from other repositories

test-reporter

Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.

nrslib/takt · 0 tokens

executor

Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…

Nanako0129/pilotfish · 60 tokens

design-rules

Condensed 10 Golden Rules from the Agent Design Bible.

jmagly/aiwg · 0 tokens

design-advisor

Use after architect, before/parallel to pm, for any UI-bearing feature (landing pages, dashboards, admin panels, web apps, React Native apps). Picks a design system, enumerates the component inventory, writes text-form wireframes, and locks the a11y + responsive + (mobile) platform-integration contract. Outputs…

avelikiy/great_cto · 89 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 132 tokens

mlops-reviewer

MLOps / model lifecycle pre-implementation reviewer. Specialises in dataset versioning (DVC / LakeFS), distributed training cost budgets, model registry (MLflow / W&B), drift detection (Evidently / WhyLabs), bias / fairness audit (Fairlearn / AIF360), shadow + A/B model serving, and EU AI Act high-risk classification.…

avelikiy/great_cto · 105 tokens