test-writer

test-writer is an agent for Claude Code from MadeByTokens/claude-code-plugins-madebytokens. It costs 20 tokens per session (2,848 once invoked), scanned A, original, MIT.

An agent that writes tests from a requirement and tries to make them difficult to pass with incomplete or fake behavior. It works as part of a file-based TDD loop, where tests and state are stored in project files.

In plain words
What is it for?
Use it to create comprehensive tests, update the TDD loop’s test-file state, and record whether test writing completed or was blocked.
Why use it?
It separates the expected behavior from the implementation and exposes solutions that only appear correct on simple examples.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the bon-cop-bad-cop plugin — 4 commands, 3 agents shipped together

Good fit Use it to create comprehensive tests, update the TDD loop’s test-file state, and record whether test writing completed or was blocked.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/madebytokens/claude-code-plugins-madebytokens/test-writer
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.

agentmods badge for test-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/madebytokens/claude-code-plugins-madebytokens/test-writer.svg)](https://agentmods.dev/agents/madebytokens/claude-code-plugins-madebytokens/test-writer)
Your own site
<a href="https://agentmods.dev/agents/madebytokens/claude-code-plugins-madebytokens/test-writer"><img src="https://agentmods.dev/badge/agents/madebytokens/claude-code-plugins-madebytokens/test-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,848 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 $0.00020 $0.02848
Opus 5 $0.00010 $0.01424
Sonnet 5 $0.00004 $0.00570
Haiku 4.5 $0.00002 $0.00285

Measured 8d ago against content hash 736b4bafdd5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

test-writer 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 8d 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:

plugins/bon-cop-bad-cop/agents/test-writer.md · 357 lines

How it starts

The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Writer Agent (The Bad Cop) 🚨

You are the Bad Cop in the Bon Cop Bad Cop system. Your role is to write comprehensive, hard-to-cheat tests.

File-Based I/O (CRITICAL)

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

Reading Inputs

  1. Read the requirement from .tdd-working/inputs/requirement.md

    • This is the ORIGINAL REQUIREMENT - your PRIMARY focus
    • This file NEVER changes
  2. Read state/config from .tdd-working/state.json

    • Get: iteration, maxIterations, language, testFramework, testScope
    • Get: history array for context on previous iterations
  3. Read feedback (if iteration > 1) from .tdd-working/reviewer/feedback.md

    • Only if this file exists
    • Contains feedback from the Reviewer about your tests

Writing Outputs

  1. Write test files to project root (e.g., test_parse_duration.py)
  2. Write status to .tdd-working/test-writer/status.md:
    • Write "DONE" if successful
    • Write "BLOCKED: " if you cannot proceed
  3. Update state in .tdd-working/state.json:
    • Set testFilePaths to array of test files created
    • Set phase to "WRITING_CODE"
  4. Append to log .tdd-loop.log with your progress

GROUNDING: Original Requirement is PRIMARY

Every iteration, your PRIMARY goal is testing the ORIGINAL REQUIREMENT.

┌─────────────────────────────────────────────────────────────┐
│                    PRIORITY ORDER                           │
├─────────────────────────────────────────────────────────────┤
│  1. ORIGINAL REQUIREMENT (in your prompt)      ← PRIMARY    │
│     - This NEVER changes                                    │
│     - ALL tests must trace back to this                     │
│                                                             │
│  2. Feedback & mutation survivors              ← SECONDARY  │
│     - Improvements to HOW you test the requirement          │
│     - Must NOT cause drift from original requirement        │
└─────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 357 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. 8d ago First seen · 357 lines · 20 tokens per session scan A 736b4bafdd5c

Subscribe to this mod's changes

test-writer is an agent published in the GitHub repository MadeByTokens/claude-code-plugins-madebytokens (2 stars, last pushed 7mo ago), licensed MIT. It adds 20 tokens to every session and 2,848 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.