patpat-automation

patpat-automation is a skill for Cursor from goiltpatpat/patpat. It costs 49 tokens per session (453 once invoked), scanned A, original, MIT.

A planning guide for building a safe automation that connects a named service, trigger, and verification process. It defines what may be written, how duplicate events are handled, where secrets come from, how failures are reversed, and how the automation can be stopped.

In plain words
What is it for?
Use it to design issue-triage loops and other provider integrations with controlled writes, retries, deduplication, dry runs, verification, compensation, and a kill switch.
Why use it?
It prevents an automation from acting with unclear authority or repeating an external action unexpectedly. Missing write-critical details cause it to stop with a configuration checklist instead of producing runnable automation.

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 design issue-triage loops and other provider integrations with controlled writes, retries, deduplication, dry runs, verification, compensation, and a kill switch.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-automation"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 453 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 $0.00049 $0.00453
Opus 5 $0.00024 $0.00227
Sonnet 5 $0.00010 $0.00091
Haiku 4.5 $0.00005 $0.00045

Measured 7d ago against content hash 7655de0be189, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

patpat-automation 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 7d 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-automation/SKILL.md · 24 lines

What it actually says

Patpat Automation

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

Read boundary discipline, idempotent effects, and preserve safety. Apply the automation design playbook. For a named issue-source triage and reproduce loop, also apply the issue loop playbook. Do not copy a host automation pack or enable a scheduler.

Require a concrete provider, immutable trigger identity, trusted coordinator, exact allowed writes, secret source outside the repository, idempotency key, dedupe behavior, immediate preflight, bounded retries and cost, safe test surface, verifier, and kill switch. Require compensation when reversal is possible; otherwise name the irreversible boundary and fail before it when state or authority is uncertain. Fail closed when any write-critical field is missing: return a configuration checklist and do not produce runnable or enabled automation.

Keep external writes under one coordinator. Give workers no credentials, write tools, or posting instructions. Default generated automation to disabled and test it against a sandbox or dry-run surface.

Enabling, scheduling, posting, filing, publishing, or deployment requires explicit authority immediately before the action. A provider-triggered issue loop may open only a draft pull request by default. Ready-PR delivery requires separate fresh interactive delivery intent (not activation alone).

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. 7d ago Changed 7655de0be189
  2. 11d ago First seen · 24 lines · 49 tokens per session scan A 7a22c4385019

Subscribe to this mod's changes

patpat-automation is a skill published in the GitHub repository goiltpatpat/patpat (1 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 453 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.