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/mintuz/skills/agents-mdgit clone --depth 1 https://github.com/mintuz/skillsWhat 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 | $0.01427 | $0.01427 |
| Opus 5 | $0.00714 | $0.00714 |
| Sonnet 5 | $0.00285 | $0.00285 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- skills CLAUDE.md — 95% identical, 32 lines differ
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
Project Overview
Codex plugin marketplace containing seven plugins for software development and personal productivity workflows:
- core – memory, commit hygiene, refactoring, prompt refinement, and branch review
- web – CSS, React, Tailwind, testing, refactoring, and design practices
- typescript – strict, schema-first TypeScript guidance
- system-design – Mermaid diagram generation from code
- product-management – PRD creation, status updates, and task orchestration
- app – Swift iOS testing, App Intent-first development, and SwiftUI architecture
- life – personal life management with GPS method for goal achievement
Plugin Architecture
Plugins extend Codex with three types of content:
- Agents - Autonomous subprocesses with specialized tools and context (defined in
agents/*.md) - Skills - Knowledge bases that load into context (defined in
skills/*/SKILL.md) - Commands - Slash commands for quick actions (defined in
commands/*.md)
The marketplace registry (.Codex-plugin/marketplace.json) indexes all plugins, while each plugin's manifest (plugin.json) defines metadata. Skills listed in marketplace.json become user-invocable (e.g., /skill core:commit-messages), while unlisted skills are only loaded by other skills or agents.
Repository Structure
.Codex-plugin/marketplace.json # Marketplace registry (plugin metadata)
src/
core/
.Codex-plugin/plugin.json
agents/ # compare-branch, refactor
skills/ # commit-messages, expectations, learn, pr, writing
web/
.Codex-plugin/plugin.json
skills/ # css, frontend-testing, react, react-testing, refactoring, tdd, web-design
typescript/
.Codex-plugin/plugin.json
skills/ # typescript-best-practices
system-design/
.Codex-plugin/plugin.json
skills/ # mermaid-generator
product-management/
.Codex-plugin/plugin.json
app/
.Codex-plugin/plugin.json
skills/ # app-intent-driven-development, swift-testing
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.
- 2d ago First seen · 178 lines · 1,427 tokens per session scan A 9e07f81b74b8
skills AGENTS.md is an instructions file published in the GitHub repository mintuz/skills (24 stars, last pushed 9d ago), licensed MIT. It adds 1,427 tokens to every session, about $0.0071 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 2026-08-30.
Other instructions, from other repositories
letta AGENTS.md
Instructions for letta-ai/letta, covering agents.md, prohibited uses, use the current letta implementation and historical inspection only.
wcgw CLAUDE.md
Instructions for rusiaaman/wcgw, covering alignment instructions to contribute to this repository, hard rules, coding mantras, reduce states and dependencies between the states and put burden on type checker not the code reader.
braindb CLAUDE.md
Instructions for dimknaf/braindb, covering braindb — claude instructions, ⚠ tool priority — read this first, it overrides habit, at the start of every session, 1. get always-on rules (behavioral guidelines) and project structure.
OmicsClaw AGENTS.md
Instructions for TianGzlab/OmicsClaw, covering agents.md — omicsclaw guide for ai coding agents, repository working contract, project overview, setup and pip install -e .
OmicsClaw CLAUDE.md
Instructions for TianGzlab/OmicsClaw, covering claude.md — omicsclaw agent instructions, repository maintenance contract, agent skills, issue tracker and triage labels.
autogen copilot-instructions.md
Copilot instructions for microsoft/autogen, covering autogen multi-agent ai framework, working effectively, prerequisites and environment setup, python development workflow and quick validation (under 1 second each).