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.
npx skills add goiltpatpat/patpat --skill patpat-reviewgit clone --depth 1 https://github.com/goiltpatpat/patpatWrote 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/skills/goiltpatpat/patpat/patpat-review)<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-review"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-review/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/skills/goiltpatpat/patpat/patpat-review"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-review.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 | $0.00040 | $0.00517 |
| Opus 5 | $0.00020 | $0.00259 |
| Sonnet 5 | $0.00008 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
patpat-review 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 6d 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patpat Review
When invoked directly, read the operating protocol in full. Do not load the router.
Read repository truth, proof over proxy, and preserve safety. Apply the independent review playbook.
Remain read-only. Inspect the objective, proof contract, exact diff or artifact, raw verification receipts, and affected contracts. When an independent reviewer is available and authorized, give it the evidence without the implementer's intended conclusion. When extra read-only reviewers are available and authorized, give each the same intent, diff, and integrity rubric from a distinct independent-angle. Consensus outweighs a lone finding. Bucket the synthesized verdict Act on / Consider / Noted / Dismissed. Do not auto-apply.
Run the playbook's solution-integrity audit before general quality review. Reject evidence laundering, unexplained assertion weakening, hardcoded fixture answers, and proof that bypasses the claimed authoritative surface. Bind evidence to the exact candidate revision or reproducible working-tree snapshot; require a committed head only for commit- or delivery-bound claims.
Findings and reporting
When the main issue is a change in shape, prefer a diff-shaped or tree explanation from earned representation over long prose. Report findings first, ordered by blocker, high, medium, then low. Tie every finding to a file, symbol, behavior, or receipt and explain the concrete impact. Exclude speculative style preferences. For each accepted issue, recommend the smallest safe correction and required re-verification.
State no findings only after checking correctness, solution integrity, regressions, contracts, safety, performance implications, side effects, generated noise, and evidence mismatch. Review does not replace verification and never authorizes merge or delivery.
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.
- 6d ago Changed e181f47e5f08
- 7d ago Changed 5cf336a35089
- 11d ago First seen · 25 lines · 40 tokens per session scan A 5725fbab8dcb
patpat-review is a skill published in the GitHub repository goiltpatpat/patpat (1 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 517 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 2026-08-31.
Other skills, from other repositories
sdd-apply
Skill "sdd-apply" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, purpose, what you receive and execution and persistence contract.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
sdd-verify
Skill "sdd-verify" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, activation contract, hard rules and decision gates.
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.