cat-skills AGENTS.md

cat-skills AGENTS.md is an instructions file for Codex, OpenCode from catcatcatstudio/cat-skills. It costs 407 tokens per session, scanned A, original, MIT.

A guide to a collection of coding-agent skills, stored as separate instruction sets in a project folder. The listed skills cover tasks such as researching, planning, testing, reviewing, and keeping project notes.

In plain words
What is it for?
Use it to discover available commands such as /eat for extracting knowledge from web content, /architect for staged builds, /fortify for testing, or /memento for handing context to a new session.
Why use it?
It helps an agent choose the right instructions for a task and find the related reference files. This makes repeated project work more consistent.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/catcatcatstudio/cat-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/catcatcatstudio/cat-skills

Made for: Codex, OpenCode.

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 cat-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/catcatcatstudio/cat-skills/agents-md.svg)](https://agentmods.dev/instructions/catcatcatstudio/cat-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/catcatcatstudio/cat-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/catcatcatstudio/cat-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 407 This file is loaded in full into every session.
When invoked 407 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00407 $0.00407
Opus 5 $0.00204 $0.00204
Sonnet 5 $0.00081 $0.00081
Haiku 4.5 $0.00041 $0.00041

Measured 5d ago against content hash fdb45ad4dc54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cat-skills 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 5d 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.

AGENTS.md · 32 lines

What it actually says

cat-skills

AI agent skills by catcatcat. Each skill is a self-contained instruction set in skills/.

Skill Directory

Skill Trigger Description
eat /eat Knowledge extraction from URLs — YouTube, articles, podcasts, X threads
notebook /notebook Project notes — decisions, failures, lessons, context recovery
architect /architect Staged build methodology — spike, design, plan, build
recon /recon Pre-build intelligence — best practices, pitfalls, architecture research
xray /xray X/Twitter content intelligence — scout, pulse, track, mirror, prospect
elevate /elevate Expert elevation — shifts model from executor to critical advisor
prodev /prodev Engineering standard enforcement — ownership, blast radius, anti-sycophancy
memento /memento Context handoff for fresh sessions
liquid-cat-physics /liquid-cat-physics Autonomous deep-work loop — expert lens + prodev standard, confidence gating, persists, loops
fortify /fortify Testing infrastructure, coverage, and mutation testing
vet /vet Thorough codebase investigation — find every problem, plan fixes, execute

Reference Files

File Path
Build methodology skills/architect/references/methodology.md
Testing obligations skills/architect/references/testing.md
Stage template skills/architect/references/stage-template.md
Notebook standalone skills/notebook/INSTRUCTIONS.md
Expert questions skills/recon/references/expert-questions.md
Research categories skills/recon/references/research-categories.md
X API reference skills/xray/references/x-api.md
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. 5d ago First seen · 32 lines · 407 tokens per session scan A fdb45ad4dc54

Subscribe to this mod's changes

cat-skills AGENTS.md is an instructions file published in the GitHub repository catcatcatstudio/cat-skills (3 stars, last pushed 9d ago), licensed MIT. It adds 407 tokens to every session, about $0.0020 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.

Related

Other instructions, from other repositories

csift AGENTS.md

AGENTS.md instructions for wdhwg001/csift, covering agents.md - csift operating manual, 1. what csift is, 3.1 data location + path encoding, 3.2 record model (one json object per line) and 3.4 askuserquestion.

wdhwg001/csift · 32,495 tokens

recursive-decomposition-skill AGENTS.md

Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.

massimodeluisa/recursive-decomposition-skill · 321 tokens

stockbit-mcp CLAUDE.md

Claude Code instructions for INo-xious/stockbit-mcp, covering claude.md, what this is, commands, the map and three invariants. do not break them; each has a test.

INo-xious/stockbit-mcp · 1,337 tokens

writer-style-skill CLAUDE.md

Claude Code instructions for solanabr/writer-style-skill, covering writer-style — voice & tone specialist, communication style, the model (in one screen), routing (by dominant job, not topic) and always-apply rules.

solanabr/writer-style-skill · 1,860 tokens

interactive-docs-skill CLAUDE.md

Claude Code instructions for adamyodinsky/interactive-docs-skill, covering interactive docs skill, structure, key conventions and testing changes.

adamyodinsky/interactive-docs-skill · 212 tokens

recursive-decomposition-skill CLAUDE.md

Instructions for massimodeluisa/recursive-decomposition-skill, a project described as: Claude Code skill for handling long-context tasks through recursive decomposition.

massimodeluisa/recursive-decomposition-skill · 3 tokens