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/run)<a href="https://agentmods.dev/commands/racecraft-lab/paddock/run"><img src="https://agentmods.dev/badge/commands/racecraft-lab/paddock/run/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.
<a href="https://agentmods.dev/commands/racecraft-lab/paddock/run"><img src="https://agentmods.dev/badge/commands/racecraft-lab/paddock/run.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00026 | $0.01510 |
| Opus 5 | $0.00013 | $0.00755 |
| Sonnet 5 | $0.00005 | $0.00302 |
| Haiku 4.5 | $0.00003 | $0.00151 |
Grade A, and why
run scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- speckit.review.run — 89% identical, 25 lines differ
- speckit.review — 89% identical, 25 lines differ
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comprehensive PR Review
Run a comprehensive pull request review using multiple specialized agents, each focusing on a different aspect of code quality.
Review Aspects (optional): "$ARGUMENTS"
Review Workflow:
-
Load Configuration
- Read the project config file at
.specify/extensions/review/review-config.yml(if it exists). - If the file does not exist, fall back to the
defaults.agentssection in the extension'sextension.yml. - Extract the
agentsmap — each key (code,comments,tests,errors,types,simplify) is a boolean toggle. - Agents set to
falseMUST be excluded from this run. Do not launch them.
- Read the project config file at
-
Determine Review Scope
- Parse arguments to see if user requested specific review aspects.
- If specific aspects were requested, run exactly those — config toggles do not apply (explicit user request overrides config).
- Default (no arguments): Run all applicable reviews that are enabled in config.
-
Available Review Aspects:
- comments - Analyze code comment accuracy and maintainability
- tests - Review test coverage quality and completeness
- errors - Check error handling for silent failures
- types - Analyze type design and invariants (if new types added)
- code - General code review for project guidelines
- simplify - Simplify code for clarity and maintainability
- all - Run all applicable reviews (default)
-
Identify Changed Files
- If the user provided a file list or explicit instructions on how to retrieve files (e.g., only staged, only unstaged, a specific folder, etc.), follow those instructions directly.
- Otherwise, you MUST execute the
{SCRIPT}with--jsonto detect changed files. Do not attempt to detect changes by runninggitcommands directly, reading git state manually, or using any other method — always delegate to the script.- The script automatically picks the best detection mode:
- Mode A (feature branch): diffs the current branch against the default branch (
main/master) from the merge-base, plus any staged and unstaged changes. - Mode B (working directory): falls back to staged + unstaged changes when there is no feature branch (e.g., working directly on the default branch).
- Mode A (feature branch): diffs the current branch against the default branch (
- JSON output:
{"branch", "default_branch", "mode", "changed_files": [...]}
- The script automatically picks the best detection mode:
- Note: The folder containing the script may be excluded from version control or hidden by search indexing. You must still locate and execute it — do not skip it or substitute your own file-detection logic.
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.
- 5d ago First seen · 175 lines · 26 tokens per session scan A 538fb8185343
run is a command published in the GitHub repository racecraft-lab/Paddock (11 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 1,510 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 2026-09-03.
Other commands, from other repositories
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, evidence, and PR-ready output.
prompt-evolve
Closed prompt-evolution loop: turn a lesson into a candidate agent prompt, gate it on held-out evals, promote only if it beats the baseline. SIA Meta→Target→Feedback ported to greatcto.
refactor-sprint
Parallel refactor sprint — fires refactor-cleaner + code-simplifier + type-design-analyzer + tdd-guide simultaneously. Full cleanup in one pass.
bugfix
TDD-driven bugfix workflow: tester writes failing test (RED) → developer fixes (GREEN) → developer refactors (REFACTOR) → reviewer validates. Accepts issue number, description, or both. Auto-creates PR unless --no-pr flag is passed.
auditar-refactor
Invoca refactor-safety-auditor — gate canônico antes de qualquer refactor. Coleta evidências (linhas, contrato externo, coverage, mutation) e retorna veredito GO/BLOCK/WARN/GO-OVERRIDE.
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.