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-verifiergit 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-verifier)<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-verifier"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-verifier/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-verifier"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-verifier.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 | $0.00041 | $0.00440 |
| Opus 5 | $0.00020 | $0.00220 |
| Sonnet 5 | $0.00008 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
patpat-verifier 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.
What it actually says
Patpat Verifier
When invoked directly, read the operating protocol in full. Do not load the router.
Read proof over proxy, preserve safety, and apply the project verifier playbook.
Inspect the actual application surface and reuse an existing harness when it can prove the claim. Otherwise create the smallest project-local verifier at .agents/skills/verify-<app>/SKILL.md with exact Launch, Doctor, Exercise, Evidence, and Cleanup procedures. Seed features/README.md plus one file per identified high-value user surface so later runs can select proof from maintained coverage instead of the easiest available path. Do not invent features to reach a quota.
Make every command executable as written. Own and stop only processes started by the verifier; never terminate by broad process name. Keep secrets out of prompts, logs, artifacts, and external calls. Preserve evidence long enough for independent inspection.
Isolate instances so two can run side by side (ports, data dirs, profiles), or refuse to double-drive a shared instance.
Prove the verifier end to end by launching the system, checking readiness, exercising one mapped workflow, inspecting the authoritative result, cleaning up, and confirming the evidence survived cleanup. When maintaining a verifier, restrict edits to its directory unless the user separately authorizes a product fix. Reconcile every feature-map entry to a concrete source entry point and live result. Report product defects instead of hiding them in verification instructions.
Proof closure
Close repository mutations through:
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 · +2 lines a964026e18c4
- 10d ago First seen · 24 lines · 41 tokens per session scan A c6349decfbba
patpat-verifier is a skill published in the GitHub repository goiltpatpat/patpat (1 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 440 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
ui-aqa-flow
Workflow for automated QA: integration and end-to-end UI test automation, page objects, etc.
qa-knowledge
To run QA engineering — requirements/gap analysis, scenario & spec design, test implementation, failure triage — over the QA knowledge base.
kafka-shadowtraffic-java
Generate a TestContainers Java test class that spins up ShadowTraffic in-process to populate a Kafka topic with synthetic data during tests. Invokes the kafka-shadowtraffic skill to build the ShadowTraffic config, then adapts it for a containerized test network and scaffolds a JUnit 5 test class with Kafka, optional…
e2e-runner
End-to-end testing specialist using Vercel Agent Browser or Playwright.
dev-testing
A testing guide that defines when to use unit, integration, API, and end-to-end tests. Unit tests check small pieces of code, while end-to-end tests check a full user flow.
dev-scenario-test
A specification for scenario testing, covering end-to-end tests, integration tests, and Artillery load tests. The input does not provide further details about its exact setup or outputs.