patpat-learn

patpat-learn is a skill for Cursor from goiltpatpat/patpat. It costs 40 tokens per session (371 once invoked), scanned A, original, MIT.

A learning tool that turns recurring engineering mistakes or verification gaps into small, durable project rules. It chooses an enforcement method such as a test, validator, lint rule, script, or focused documentation.

In plain words
What is it for?
Use it after repeated mistakes, failed checks, review findings, or user corrections to add targeted safeguards and verify that they catch the original problem.
Why use it?
It helps prevent the same failure from happening again instead of fixing each occurrence separately.

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 after repeated mistakes, failed checks, review findings, or user corrections to add targeted safeguards and verify that they catch the original problem.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-learn"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 371 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 $0.00040 $0.00371
Opus 5 $0.00020 $0.00186
Sonnet 5 $0.00008 $0.00074
Haiku 4.5 $0.00004 $0.00037

Measured 8d ago against content hash bb4d68765302, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

patpat-learn 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 8d 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-learn/SKILL.md · 24 lines

What it actually says

Patpat Learn

When invoked directly, read the operating protocol in full. Do not load the router.

Read encode lessons, repository truth, and apply the learning playbook.

Use evidence from the active task: user corrections, failed verification, repeated retries, review findings, or verifier defects. Separate one-off facts from recurring failure modes. Encode only the latter.

Choose the strongest narrow mechanism that prevents recurrence: type or contract, focused test, lint or validator rule, deterministic script, workflow instruction, then documentation. Prefer enforcement over reminders and update an existing authoritative location before creating a new file. Mine this conversation for recurring working-style or failure rules. Propose edits to existing files only. Present the proposal and wait for approval. Do not auto-apply. There is no new SKILL.md and no *-mode mint on this path. Never create a new SKILL.md. Never mint a personal *-mode skill.

Do not mine unrelated conversations or store sensitive task data. Do not modify shared or user-global rules without explicit authority. Verify that the chosen mechanism detects or prevents the original failure, then report what remains unprotected.

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. 8d ago Changed bb4d68765302
  2. 12d ago First seen · 24 lines · 40 tokens per session scan A 2cdaf2704cad

Subscribe to this mod's changes

patpat-learn 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 371 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.