patpat-verifier

patpat-verifier is a skill for Cursor from goiltpatpat/patpat. It costs 41 tokens per session (440 once invoked), scanned A, original, MIT.

A guide for creating or maintaining a project-specific checker that starts the real application, exercises it, observes the result, and cleans up.

In plain words
What is it for?
Use it to build a local verifier with launch, health check, exercise, evidence, and cleanup steps, and to prove one real workflow end to end.
Why use it?
It provides repeatable proof of user-facing behavior when a project lacks a reliable way to verify that behavior.

Skill for Cursor

Written for Cursor: shipped in a Cursor plugin.

Part of the patpat plugin — 22 skills, 1 agent, 3 hooks shipped together

Good fit Use it to build a local verifier with launch, health check, exercise, evidence, and cleanup steps, and to prove one real workflow end to end.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goiltpatpat/patpat/patpat-verifier
Install

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.

Any agent
npx skills add goiltpatpat/patpat --skill patpat-verifier
Clone the repo
git clone --depth 1 https://github.com/goiltpatpat/patpat

Made for: Cursor.

Or install patpat, the plugin that ships this one along with the rest of its 22 skills, 1 agent, 3 hooks.

Wrote 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.

agentmods badge for patpat-verifier

README.md
[![agentmods](https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-verifier/github.svg)](https://agentmods.dev/skills/goiltpatpat/patpat/patpat-verifier)
Your own site
<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.

agentmods 80×15 button for patpat-verifier

Your own site · 80×15
<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>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 440 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash a964026e18c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

skills/patpat-verifier/SKILL.md · 26 lines

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:

Changes

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.

  1. 6d ago Changed · +2 lines a964026e18c4
  2. 10d ago First seen · 24 lines · 41 tokens per session scan A c6349decfbba

Subscribe to this mod's changes

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.