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-setupgit 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-setup)<a href="https://agentmods.dev/skills/goiltpatpat/patpat/patpat-setup"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-setup/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-setup"><img src="https://agentmods.dev/badge/skills/goiltpatpat/patpat/patpat-setup.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 | $0.00046 | $0.00733 |
| Opus 5 | $0.00023 | $0.00367 |
| Sonnet 5 | $0.00009 | $0.00147 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
patpat-setup 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patpat Setup
When invoked directly, read the operating protocol in full. Do not load the router.
Inspect the host, available CLI, source location, requested scope, and existing installation before changing anything. Keep compatibility questions read-only. Native install, update, and removal require current user authority for the exact host and user scope. Prefer the host-native plugin manager for Cursor, Codex, or Antigravity. Use scripts/install_skills.py only when the user selects an explicit compatible skills directory.
Read the agent install contract in AGENTS.md and the host commands in docs/guide/installing.md. Select one route. Do not combine native and copied installations in the same host scope.
The published source is https://github.com/goiltpatpat/patpat. The Codex plugin id is patpat@patpat.
Preview copy-based portable installation with --dry-run. Refuse guessed home directories and silent user-level installation. Native plugin managers own their installed state. The portable installer currently supports new installs only and refuses overwrite; never use or describe it as an updater or uninstaller.
Stage a working tree that contains Memory Bank or other ignored files with scripts/stage_plugin.py before native Codex or Antigravity install. A clean clone of the published repository may be installed directly. Never add or install a dirty checkout.
For Codex, require .agents/plugins/marketplace.json and .codex-plugin/plugin.json. Prefer codex plugin marketplace add goiltpatpat/patpat then codex plugin add patpat@patpat. For a dirty local tree, add the staged distribution instead. Inspect codex plugin list --json, then start a new task before testing $patpat-loop discovery.
For Antigravity, validate the clean clone or staged path before installation, install only that explicit path, inspect the installed plugin list, and test skill invocation in a fresh session.
For Cursor, treat native plugin loading as experimental. Use the explicit project skills directory after proving the host reads it, then reload Cursor. Do not claim /add-plugin patpat or native invocation until Cursor reloads the plugin and invokes patpat-loop in a real project.
For another agent, first prove that it supports the Agent Skills folder contract. Ask for or discover its exact project-scoped skill directory. If no supported discovery contract exists, stop with installation instructions instead of copying files into a guessed location.
After install, invoke with the host form from the installation guide. Cursor uses /patpat. Codex uses $patpat. Portable hosts use Use patpat to ....
Report the detected host, selected scope, exact destination or marketplace, pre-existing conflicts, command receipts, discovered skill count, invocation result, and removal path. Classify package validation separately from prompt-time discovery.
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.
- 9d ago First seen · 38 lines · 46 tokens per session scan A edfdff37548d
patpat-setup is a skill published in the GitHub repository goiltpatpat/patpat (1 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 733 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
Repository Knowledge Management
Create and maintain the Repository Knowledge Base using the official Agentic Engineering playbooks.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…