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 agentmods add instructions/goiltpatpat/patpat/agents-mdgit 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/instructions/goiltpatpat/patpat/agents-md)<a href="https://agentmods.dev/instructions/goiltpatpat/patpat/agents-md"><img src="https://agentmods.dev/badge/instructions/goiltpatpat/patpat/agents-md.svg" alt="Measured on agentmods" 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 | $0.00644 | $0.00644 |
| Opus 5 | $0.00322 | $0.00322 |
| Sonnet 5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
patpat AGENTS.md 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 yesterday.
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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent install contract
This file is the machine-readable install surface. Engineering workflows live in skills/. Do not invent a home directory, updater, uninstaller, or Cursor marketplace command.
Canonical skill tree: skills/. Host adapters are thin manifests over that tree. Read docs/guide/installing.md for host commands and skills/patpat-setup/SKILL.md when that skill is already loadable.
Detect, then choose one route
- Identify the host, available CLI, requested scope, and source.
- Select one route. Do not combine native plugin installation with copied skills in the same host scope.
- Stage a working tree that contains Memory Bank or other ignored files before any native Codex or Antigravity install.
Published source: https://github.com/goiltpatpat/patpat. Plugin id: patpat@patpat.
| Host | Install |
|---|---|
| Grok CLI from GitHub | grok plugin install goiltpatpat/patpat --trust |
| Codex from GitHub | codex plugin marketplace add goiltpatpat/patpat then codex plugin add patpat@patpat |
| Codex from a dirty local tree | python3 scripts/stage_plugin.py --target /absolute/path/to/patpat-dist then marketplace-add that staged path |
| Antigravity from a clean clone | agy plugin validate /absolute/path/to/patpat then agy plugin install /absolute/path/to/patpat |
| Antigravity from a dirty local tree | stage first, then validate and install the staged path |
| Cursor | Native load is experimental. Use the portable route until a live project load is proven. |
| Other Agent Skills hosts | Prove the project skill directory, then python3 scripts/install_skills.py --target /absolute/proven/skills-dir --dry-run |
After install
Start a fresh task or session. Package list output does not prove prompt-time discovery.
Explicit /patpat, /patpat-loop, $patpat, or $patpat-loop activation authorizes the Patpat loop, proof, and verify. Default commit-and-PR requires delivery intent; see the operating protocol and default-delivery playbook. Higher-priority repository rules and local only still win. Merge requires explicit land or merge language.
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.
- yesterday Changed d2a2449d2bdd
- 5d ago First seen · 40 lines · 644 tokens per session scan A f05121e28b17
patpat AGENTS.md is an instructions file published in the GitHub repository goiltpatpat/patpat (1 stars, last pushed yesterday), licensed MIT. It adds 644 tokens to every session, about $0.0032 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 instructions, from other repositories
agentic-engineering-for-apache-kafka AGENTS.md
Instructions for lensesio/agentic-engineering-for-apache-kafka, covering agents.md, project overview, project structure, skill structure conventions and kafka skills.
awesome-copilot-id AGENTS.md
AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
kleosrules AGENTS.md
AGENTS.md instructions for kleosr/kleosrules, covering agents.md — repository agent handbook, law, pack, skills (on demand) and workflows.
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.
gandalf CLAUDE.md
Instructions for sebacaro/gandalf, covering gandalf — cli para spec driven development, comandos, activar entorno, ejecutar directamente and o con gandalf global (después de install.sh).