skills: Instructions file for Codex

AGENTS.md

skills AGENTS.md is an instructions file for Codex, OpenCode from davidondrej/skills. It costs 1,478 tokens per session, scanned A, original, MIT.

A project-wide instruction file for the skills repository. It records rules for responses, source-of-truth files, local previews, product decisions, and code quality.

In plain words
What is it for?
Use it to guide agent behavior while working in the repository, especially for concise responses, checking authoritative files, and making development decisions.
Why use it?
It gives coding agents consistent guidance instead of making each task depend on unstated conventions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is davidondrej/skills's own configuration. It tells Codex and OpenCode how to work on skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skills configures →

About the project

David Ondrej's Agent Skills is a repository of reusable instruction packages for AI coding, research, and workflow agents. Each skill describes a focused process for tasks such as code improvement, research, documentation, transcript work, and agent coordination. The catalogue entries are the repository's own skills and related agent configuration.

davidondrej/skills · 3,967 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to davidondrej/skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/davidondrej/skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/davidondrej/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 skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/davidondrej/skills/agents-md.svg)](https://agentmods.dev/instructions/davidondrej/skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/davidondrej/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/davidondrej/skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,478 This file is loaded in full into every session.
When invoked 1,478 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01478 $0.01478
Opus 5 $0.00739 $0.00739
Sonnet 5 $0.00296 $0.00296
Haiku 4.5 $0.00148 $0.00148

Measured today against content hash 057e2e433cbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 today.

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 · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IMPORTANT GLOBAL PRINCIPLE

  • this file should NEVER have instructions about a specific project

RESPONSES

  • Make ALL of your responses clear & very concise
  • Use simple & easy-to-understand language
  • write in short sentences, in plain English
  • the User cannot see tool outputs, show him everything in text

BEHAVIOR

  • For local previews, use localhost. Do not expose bb connect / getbb.app share links unless the user asks.
  • for major product / software / architecture decisions, see DECISIONS vs EXECUTION
  • When opening a local file in a named app, use the terminal open -a command when it is sufficient. Do not use UI automation for this simple action.
  • NEVER use the multiple-choice question UI. Ask the User in plain text.
  • Never suggest that the user switch to Plan Mode, and never switch to it unless the user explicitly asks.

SOURCE OF TRUTH

  • treat source-of-truth files (README, schema, decision logs) as authoritative
  • Before creating a named top-level folder, check for an existing sibling under ~; never assume it is relative to the current directory.

CODE QUALITY

  • totally ignore development time when making dev decisions
  • we use frontier AI coding agents (refactors & code changes that would take weeks or months now take minutes or hours)
  • instead, focus on quality, simplicity, robustness, scalability
  • keep the tech stack simple, popular, and maintainable
  • prefer existing patterns, helpers, and conventions over new abstractions
  • write simple, readable, modular code with clear ownership
  • add comments only for non-obvious intent, tradeoffs, or constraints

BUG FIXES

  • When doing bug fixes, always start with reproducing the bug in an E2E setting as closely aligned with how an end user would experience it. This makes sure you find the real problem so your fix will actually solve it.
  • Do not delete, skip, weaken, or narrow tests to make a task pass.
  • Prefer behavior-focused tests over private implementation tests.

DOCUMENTATION

  • Keep docs concise, operational, and source-backed.
  • see the project’s docs/ folder for project-specific documentation
  • Do not bloat AGENTS.md, CLAUDE.md, README files (only the user can add to them)
  • Ensure every important subfolder has its own AGENTS.md when it has durable ownership, contracts, commands, workflows, or rules that future agents need to follow.
  • Parent AGENTS.md files should describe broad rules and child-doc indexes. Child AGENTS.md files should describe local contracts.

Read the full file on GitHub · 125 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. today Changed · +2 tokens per session 057e2e433cbc
  2. 2d ago First seen · 125 lines · 1,476 tokens per session scan A caa6e812d10d

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository davidondrej/skills (3,967 stars, last pushed yesterday), licensed MIT. It adds 1,478 tokens to every session, about $0.0074 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 2026-09-05.

Related

Other instructions, from other repositories

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

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

next.js AGENTS.md

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

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 · 4,469 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

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