patpat-engineer

patpat-engineer is a skill for Cursor from goiltpatpat/patpat. It costs 44 tokens per session (267 once invoked), scanned A, original, MIT.

A tightly scoped worker procedure for carrying out one implementation task assigned by an integration owner. It requires clear boundaries, allowed file changes, and a defined way to prove the work is correct.

In plain words
What is it for?
Use it for one bounded coding change, followed by targeted checks and a report of changed files, evidence, blockers, and risks.
Why use it?
It prevents delegated workers from changing unrelated code or taking over decisions that belong to the owner.

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 for one bounded coding change, followed by targeted checks and a report of changed files, evidence, blockers, and risks.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-engineer/github.svg)](https://agentmods.dev/skills/goiltpatpat/patpat/patpat-engineer)
Your own site
<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-engineer"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-engineer/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-engineer

Your own site · 80×15
<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-engineer"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 267 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 $0.00044 $0.00267
Opus 5 $0.00022 $0.00133
Sonnet 5 $0.00009 $0.00053
Haiku 4.5 $0.00004 $0.00027

Measured 9d ago against content hash 43e9d826d46e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

patpat-engineer 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 9d 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-engineer/SKILL.md · 22 lines

What it actually says

Patpat Engineer

Read the operating protocol in full before acting. Do not load the router. Accept work only when the delegation names the objective, owned files or boundary, forbidden scope, allowed mutations, proof contract, and integration owner.

Do not spawn another worker. Do not touch shared or out-of-scope files. Stop on ownership overlap, contract conflict, missing authority, or evidence that invalidates the slice. Never commit, push, publish, merge, deploy, or communicate externally.

Implement the smallest safe slice and run its targeted check. Return changed files, raw evidence, blockers, and risks. Treat the result as a candidate artifact: the integration owner must inspect and verify it independently before integration.

Worker self-report never satisfies verification or review; the integration owner must inspect the candidate artifact.

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. 9d ago First seen · 22 lines · 44 tokens per session scan A 43e9d826d46e

Subscribe to this mod's changes

patpat-engineer is a skill published in the GitHub repository goiltpatpat/patpat (1 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 267 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.