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/racecraft-lab/PaddockWrote 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/racecraft-lab/paddock/cleanup)<a href="https://agentmods.dev/commands/racecraft-lab/paddock/cleanup"><img src="https://agentmods.dev/badge/commands/racecraft-lab/paddock/cleanup.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 | $0.00030 | $0.03843 |
| Opus 5 | $0.00015 | $0.01921 |
| Sonnet 5 | $0.00006 | $0.00769 |
| Haiku 4.5 | $0.00003 | $0.00384 |
Grade A, and why
cleanup 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Goal
Perform a final quality gate after implementation. Review all changes made during implementation, identify technical debt, and handle issues according to severity:
- Small issues: Fix immediately (Scout Rule) - with user confirmation
- Medium issues: Create follow-up tasks in tasks.md
- Large issues: Generate detailed analysis with options in tech-debt-report.md
Operating Constraints
Constitution Authority: The project constitution (.specify/memory/constitution.md) is non-negotiable. Any cleanup action that would violate constitution principles is forbidden. If a fix would conflict with a MUST principle, escalate to large issue instead of fixing.
Linter Deference: For style and formatting issues, defer to the project's configured linters. Do NOT manually fix issues that linters should handle - instead, run the linter with auto-fix if available.
Preserve User Intent: If code appears intentional (e.g., commented code with explanation, disabled tests with TODO reason), do NOT auto-fix. Escalate to medium issue for user review.
Execution Steps
1. Initialize Cleanup Context
Run {SCRIPT} once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths:
- SPEC = FEATURE_DIR/spec.md
- PLAN = FEATURE_DIR/plan.md
- TASKS = FEATURE_DIR/tasks.md
- CONSTITUTION = .specify/memory/constitution.md
- TECH_DEBT_REPORT = FEATURE_DIR/tech-debt-report.md
Abort with error if TASKS does not exist or has no completed tasks (implementation not run). For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'''m Groot' (or double-quote if possible: "I'm Groot").
2. Load Implementation Context
Load minimal necessary context from each artifact:
From tasks.md:
- All completed tasks (marked
[X]or[x]) - File paths mentioned in completed tasks
- Implementation phases that were executed
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.
- 3d ago First seen · 482 lines · 30 tokens per session scan A 6116f4a24cd5
cleanup is a command published in the GitHub repository racecraft-lab/Paddock (11 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 3,843 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 2026-09-03.
Other commands, from other repositories
gh-triage
GitHub OSS maintainer lifecycle triage, review, and approval management.
codebase-review
Review an entire codebase for architecture, engineering health, and exploitable risk; generate a prioritized remediation plan, an evidence-anchored system knowledge document, or both.
afe
Evaluate feature - code review or comparison (shortcut for feature-eval).
factory-ticket
Implement exactly one already-claimed Linear ticket in the current worktree.
Hexagonal.Gatekeeper
Your role is to perform a deep, architecture-focused code review on a specific branch. You must validate that all changes strictly follow Hexagonal Architecture (Ports & Adapters) principles and align with the existing codebase patterns.
assess
Run an AI literacy assessment — scan the repo for evidence, ask clarifying questions, produce a timestamped assessment document, apply immediate habitat fixes, recommend workflow changes, capture a reflection, and add a literacy level badge to the README.