An agent that reviews tests and implementation files for a TDD loop. It checks whether the tests match the requirement, whether the code passes them honestly, and whether mutation testing finds weaknesses.

Use it to read the loop’s requirement, state, tests, and implementation, then write a verdict and feedback for the next iteration.

It provides an objective review instead of accepting passing tests without checking their quality or coverage of the requirement.

reviewer — Agent for Claude Code by MadeByTokens

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.

Clone the repo

git clone --depth 1 https://github.com/MadeByTokens/claude-code-plugins-madebytokens

Made for: Claude Code.

Or install bon-cop-bad-cop, the plugin that ships this one along with the rest of its 4 commands, 3 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/madebytokens/claude-code-plugins-madebytokens/reviewer/github.svg)](https://agentmods.dev/agents/madebytokens/claude-code-plugins-madebytokens/reviewer)

Your own site

<a href="https://agentmods.dev/agents/madebytokens/claude-code-plugins-madebytokens/reviewer"><img src="https://agentmods.dev/badge/agents/madebytokens/claude-code-plugins-madebytokens/reviewer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/madebytokens/claude-code-plugins-madebytokens/reviewer"><img src="https://agentmods.dev/badge/agents/madebytokens/claude-code-plugins-madebytokens/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,660 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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.04660
Opus 5	$0.00010	$0.02330
Sonnet 5	$0.00004	$0.00932
Haiku 4.5	$0.00002	$0.00466

Measured 9d ago against content hash aa661932db1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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:

reviewer — 100% identical, 0 lines differ

plugins/bon-cop-bad-cop/agents/reviewer.md · 543 lines

How it starts

The opening of the file, as written. The whole thing — 543 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewer Agent (The Good Cop) 👮

You are the Good Cop in the Bon Cop Bad Cop system. You are fair but thorough - the final arbiter of truth.

File-Based I/O (CRITICAL)

You MUST read your inputs from files, not from the prompt.

Reading Inputs

Read the requirement from .tdd-working/inputs/requirement.md
- This is the ORIGINAL REQUIREMENT - use for alignment checking
- This file NEVER changes
Read state/config from .tdd-working/state.json
- Get: testFilePaths array - paths to test files
- Get: implFilePaths array - paths to implementation files
- Get: mutationThreshold, testCommand, language, iteration
- Get: history array for context on previous iterations
Read test files from paths in testFilePaths
Read implementation files from paths in implFilePaths

Writing Outputs

Write verdict to .tdd-working/reviewer/verdict.md:
- Write one of: "ALL_PASS", "WEAK_TESTS", or "WEAK_CODE"
Write feedback to .tdd-working/reviewer/feedback.md:
- Detailed feedback for the next iteration
- Include requirement quote to prevent drift
Update state in .tdd-working/state.json:
- Set lastVerdict, mutationScore, phase
- Append to history array
Append to log .tdd-loop.log with your progress

You MUST run tests and mutation testing using the Bash tool.

Your Mindset

You're the reasonable one, but you have a job to do. Both the Bad Cop (Test Writer) and The Suspect (Code Writer) might cut corners, and it's your job to catch them. You have tools at your disposal: test execution, mutation testing, and pattern detection. Mutation testing is your lie detector.

Information Boundaries

You can see:

Everything: tests, code, all history
All previous verdicts and feedback
Patterns across iterations (detect stalemates, collusion)

Your responsibility:

Filter feedback so agents only see their own
Never reveal one agent's struggles to the other

Read the full file on GitHub · 543 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.

9d ago First seen · 543 lines · 19 tokens per session scan A aa661932db1f

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository MadeByTokens/claude-code-plugins-madebytokens (2 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 4,660 once invoked, about $0.0001 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.

Code review TDD Testing

pr-test-analyzer

Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Typical triggers include the user asking whether tests on a freshly-created PR are thorough…

anthropics/claude-plugins-official · 101 tokens

Principal software engineer

Provide principal-level software engineering guidance with focus on engineering excellence, technical leadership, and pragmatic implementation.

github/awesome-copilot · 23 tokens

sdd-apply

Implement SDD tasks with strict TDD evidence and review workload guard.

Gentleman-Programming/gentle-pi · 19 tokens

sdd-verify

Verify implementation against SDD specs, tasks, strict TDD evidence, and review workload boundaries.

Gentleman-Programming/gentle-pi · 24 tokens

nw-software-crafter-reviewer

Use for review and critique tasks. Code-quality + TDD-discipline review of Outside-In TDD implementations. Runs on Haiku for cost efficiency.

nWave-ai/nWave · 39 tokens

senior-dev

Usar para implementación de código con TDD estricto, refactoring guiado y respuesta a code reviews. Se activa en la fase 3 (desarrollo) de /alfred-dev:feature y en la fase de diagnóstico y corrección de /alfred-dev:fix. También se puede invocar directamente para tareas de implementación, refactoring o consultas sobre…

686f6c61/alfred-dev · 263 tokens