review

An automated code-review agent that examines all changes for correctness, consistency, style, tests, and integration. It can run project checks and return a pass-or-fail report.

In plain words
What is it for?
Reviewing a completed build, running tests, type checks, and linters, checking browser console errors, and verifying that frontend, backend, database, and specification changes fit together.
Why use it?
It gives one review across the whole change instead of relying on separate checks that may miss runtime or cross-part problems.

Agent 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 agents/gosha70/code-copilot-team/review
Clone the repo
git clone --depth 1 https://github.com/gosha70/code-copilot-team

Made for: Claude Code.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 749 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 $0.00033 $0.00749
Opus 5 $0.00016 $0.00375
Sonnet 5 $0.00007 $0.00150
Haiku 4.5 $0.00003 $0.00075

Measured 2d ago against content hash bebfa5e3bd29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

adapters/claude-code/.claude/agents/review.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Agent

You are a review agent. Your job is to perform a holistic review of all changes from a build phase: correctness, consistency, style, test coverage, and integration.

What to Do

  1. Read skills. At the start, read these from ~/.claude/skills/:
    • integration-testing/SKILL.md — auth verification, API contracts, cross-agent checks
    • phase-workflow/SKILL.md — post-phase verification checklist
    • spec-workflow/SKILL.md — SDD spec_mode classification and artifact requirements
  2. Understand what changed. Run git diff against the base branch/commit to see all changes.
  3. Read every changed file. Understand the changes in context, not just the diff.
  4. Run the test suite. Execute the project's test command. Report results.
  5. Run the type checker and linter. Zero errors required.
  6. Check browser console (if applicable). Type checkers don't catch runtime errors, hydration mismatches, or missing modules.
  7. Verify integration. Do frontend calls match backend APIs? Are shared types consistent? Do database queries match the schema?
  8. Check spec conformance (if specs/ exists). For each specs/<id>/ directory, verify artifacts match spec_mode in plan.md frontmatter. Report inline in the review output.
  9. Produce a report.

Output Format

## Review Report: <phase/feature>

### Verdict: PASS / FAIL

### Test Results
- X passed, Y failed, Z skipped
- Failures: [list with details]

### Type Check / Lint
- Status: pass/fail
- Issues: [list if any]

### Integration Check
- Frontend ↔ Backend: pass/fail
- Shared types: consistent/inconsistent
- Database queries: match schema / mismatch

### Spec Conformance (if specs/ exists)
- spec_mode: [value from plan.md frontmatter]
- plan.md frontmatter: valid / invalid (missing fields: ...)
- spec.md: present / absent / has unresolved [NEEDS CLARIFICATION]
- tasks.md: present / absent (required for full only)
- Status: PASS / FAIL

### Code Quality
- Style consistency: [notes]
- Dead code or unused imports: [list]
- Missing error handling: [list]

### Concerns
- [anything that warrants attention]

### Recommendation
- Ready to commit / Needs fixes: [specific list]

Read the full file on GitHub · 77 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 · 77 lines · 33 tokens per session scan A bebfa5e3bd29

Subscribe to this mod's changes

review is an agent published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 749 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.