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.
git clone --depth 1 https://github.com/MadeByTokens/bon-cop-bad-copWrote 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.
[](https://agentmods.dev/commands/madebytokens/bon-cop-bad-cop/help)<a href="https://agentmods.dev/commands/madebytokens/bon-cop-bad-cop/help"><img src="https://agentmods.dev/badge/commands/madebytokens/bon-cop-bad-cop/help.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00009 | $0.00582 |
| Opus 5 | $0.00005 | $0.00291 |
| Sonnet 5 | $0.00002 | $0.00116 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
help 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.
This is a copy
100% identical to help — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
/help Command
When the user runs /help, display the following information:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🎭 **Bon Cop Bad Cop - Adversarial TDD Plugin**
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Three-agent adversarial TDD loop where agents keep each other honest.
**Commands:**
/bon-cop-bad-cop:tdd-loop "requirement" [options]
/bon-cop-bad-cop:tdd-loop --requirement-file <path> [options]
/bon-cop-bad-cop:tdd-loop "extra notes" --requirement-file <path> [options]
Start a new TDD loop with the given requirement.
Options:
--requirement-file PATH Load requirement from markdown file
(can combine with inline text for notes)
--max-iterations N Max loop iterations (default: 15)
--mutation-threshold X Required mutation score 0.0-1.0 (default: 0.8)
--test-scope SCOPE unit | integration | both (default: unit)
--language LANG Override auto-detection (python, javascript,
typescript, rust, go, java, ruby)
/bon-cop-bad-cop:tdd-status
Check the current TDD loop status and progress.
/bon-cop-bad-cop:cancel-tdd
Cancel the active TDD loop.
/bon-cop-bad-cop:help
Display this help message.
**Quick Start:**
/bon-cop-bad-cop:tdd-loop "Write a function is_prime(n)"
**How It Works:**
1. Test Writer (Bad Cop) → Creates comprehensive tests
2. Code Writer (Suspect) → Implements code (sees only tests!)
3. Reviewer (Good Cop) → Validates and issues verdict
Loop continues until ALL_PASS or max iterations reached.
**Generated Files:**
.tdd-working/ - Working directory with state and agent I/O
└── state.json - Current loop state (recent 3 iterations only)
.tdd-loop.log - Complete history and detailed output (primary record)
**Context Management:**
The plugin is optimized for long-running loops (up to 15 iterations).
- Agent responses are minimal to preserve context
- History is truncated to 3 iterations in state file
- Full details are preserved in .tdd-loop.log
- Read the log file for debugging and complete history
**More Info:** See README.md for full documentation.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
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.
- 8d ago First seen · 71 lines · 9 tokens per session scan A 547ffc7212e8
help is a command published in the GitHub repository MadeByTokens/bon-cop-bad-cop (1 stars, last pushed 7mo ago), licensed MIT. It adds 9 tokens to every session and 582 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to help, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
check-dev
Type-check a Z specification with fuzz.
adr-supersede
Create a new ADR that supersedes an existing one.