codex-skills-library AGENTS.md

Repository instructions for maintaining a library of Codex skills, including how to choose skills, keep changes small, and manage generated files.

In plain words
What is it for?
Use it before changing skills, documentation, scripts, plugins, or generated catalog files, especially during project setup or takeover.
Why use it?
It helps contributors work safely in an unfamiliar repository and prevents oversized code files or edits to the wrong project area.

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/yankieldbc2/codex-skills-library/agents-md
Clone the repo
git clone --depth 1 https://github.com/YankielDBC2/codex-skills-library

Made for: Codex, OpenCode.

Per session 1,368 This file is loaded in full into every session.
When invoked 1,368 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 $0.01368 $0.01368
Opus 5 $0.00684 $0.00684
Sonnet 5 $0.00274 $0.00274
Haiku 4.5 $0.00137 $0.00137

Measured 3d ago against content hash 49986ea580b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-skills-library 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 3d 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 · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Este repositorio es una biblioteca de skills de Codex. Mantener cambios pequenos, validados y seguros.

Proposito

Antes de editar, entiende si el cambio afecta a:

  1. un skill en .agents/skills/<skill-name>/SKILL.md;
  2. la especificacion o calidad de skills en docs/;
  3. los generadores y validadores en scripts/;
  4. el paquete estable en plugins/skills-pack/;
  5. los artefactos generados en generated/ o CATALOG.md.

Skill routing by default

  • Before any task, choose the most specific applicable skill or skills.
  • If multiple skills fit, use the smallest set that fully covers the task.
  • If no exact skill fits, fall back to token-efficient-codex-run and say so explicitly.
  • For unknown or stale repos, include project-recovery-audit.
  • For bootstrap or takeover, use codex-project-intake.
  • Do not ask the user for examples when a matching skill already exists in this repo.

Hard file-size rule

  • Code-bearing files must stay at or below 400 lines.
  • If a code file is approaching the limit, refactor it before it crosses 400 lines.
  • If a file is already at or above 400 lines and needs refactoring, create a checkpoint first: copy the original file to a backup path or save a patch diff that can be compared or restored later.
  • Keep the checkpoint until the refactor passes validation.

Stack actual

  • Node.js >=20
  • ESM ("type": "module")
  • npm
  • Tests con node --test
  • CI en GitHub Actions
  • Sin dependencias runtime declaradas en package.json

Orden de lectura

Antes de cambiar algo, lee solo lo necesario:

  1. docs/CODEBASE_INDEX.md
  2. docs/SKILL_SPEC.md
  3. docs/QUALITY_RUBRIC.md
  4. docs/SKILL_ROUTING.md para la politica de selection de skills
  5. docs/PROJECT_INTAKE.md para bootstrap y takeover
  6. CONTRIBUTING.md cuando agregues o cambies skills
  7. El SKILL.md afectado y sus references/ si la tarea toca un skill concreto

Reglas del repositorio

  • .agents/skills/ es la fuente de verdad para skills editables.
  • plugins/skills-pack/ es una copia sincronizada de los skills estables.
  • CATALOG.md y generated/ son artefactos generados; no se editan a mano.
  • Los ejemplos largos van en references/, no dentro de SKILL.md.
  • Los helpers deterministas van en scripts/.
  • No agregues secretos, tokens, .env, claves privadas ni datos de cliente.
  • Mantiene cada skill con un solo objetivo claro.
  • Si cambias metadata de skills, mantenla alineada con docs/SKILL_SPEC.md.
  • Si una regla se repite, conviertela en skill, plantilla o documento reutilizable.
  • Si necesitas medir mejora real, usa docs/EFFICIENCY_SYSTEM.md y templates/project/EFFICIENCY_RUN.json.
  • Si dudas entre skills, revisa docs/SKILL_ROUTING.md antes de improvisar.
  • Usa npm run check:loc para validar el limite de 400 lineas en archivos de codigo.

Read the full file on GitHub · 141 lines

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. 3d ago First seen · 141 lines · 1,368 tokens per session scan A 49986ea580b0

Subscribe to this mod's changes

codex-skills-library AGENTS.md is an instructions file published in the GitHub repository YankielDBC2/codex-skills-library (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,368 tokens to every session, about $0.0068 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

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens