claude-skills AGENTS.md

claude-skills AGENTS.md is an instructions file for Codex, OpenCode from obeone/claude-skills. It costs 691 tokens per session, scanned A, original, MIT.

A set of repository instructions for building and maintaining Claude agent skills. It explains the skill layout, execution environment, required file format, and versioning rules.

In plain words
What is it for?
Use it when creating, checking, or releasing skills in this repository, especially Python scripts, SKILL.md files, and supporting assets or references.
Why use it?
It gives coding agents and skill authors shared rules for where files belong and how skills should be structured. This reduces inconsistent files and release mistakes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

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/obeone/claude-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/obeone/claude-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 claude-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/obeone/claude-skills/agents-md.svg)](https://agentmods.dev/instructions/obeone/claude-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/obeone/claude-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/obeone/claude-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 691 This file is loaded in full into every session.
When invoked 691 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 5.1 $0.00691 $0.00691
Opus 5 $0.00345 $0.00345
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 5d ago against content hash f63479ce2c73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to agents when working with code in this repository.

Overview: Claude Agent Skills Stack

This repository implements a decentralized "Claude Agent Skills" architecture. Each skill is self-contained and provides tools, references, and validation scripts for agents.

Execution Environment

  • Python Scripts: Use uv for dependency management whenever possible. Scripts should be executable via python <script_path>.
  • Mandatory Requirements:
    • All SKILL.md files MUST contain a YAML front-matter with name, description, and tools (as a YAML list).
    • POSIX compliance: All text files must end with a newline (\n) and use LF line endings.
    • Example front-matter:
      ---
      name: my-skill
      description: "Skill description"
      tools:
        - Read
        - Write
      ---
      

Key Paths

  • skills/<skill-name>/SKILL.md: Main entry point for a skill.
  • skills/<skill-name>/scripts/: Validation and analysis scripts.
  • skills/<skill-name>/assets/: Templates and static resources.
  • skills/<skill-name>/references/: Documentation and best practices.

Release & Versioning

Two decoupled version spaces — never align one to the other:

  • Per-skill version → SemVer. Each skill carries its own metadata.version in SKILL.md (e.g. 4.0.0), bumped major/minor/patch according to the change in that skill. Independent across skills.
  • Repo release tags → CalVer. Git tags use vYYYY.MM.MICRO (e.g. v2026.05.0, then v2026.05.1 for a second release the same month, v2026.06.0 the next month). A tag means "a publish happened" — it is not the version of any skill.

Tagging procedure:

  1. Next tag = v$(date +%Y.%m).<micro> where <micro> is the highest existing vYEAR.MONTH.* tag + 1, or 0 if none this month. Legacy SemVer tags (v4.1.0 and earlier) are ignored for this calculation.
  2. Pre-checks: main == origin/main, target commit pushed, and git rev-parse -q --verify refs/tags/<tag> shows the tag is free. The Publish Skills workflow (trigger v*) is destructive if a published tag is rewritten.
  3. Annotated + GPG-signed tag, message vYYYY.MM.MICRO - <summary>.
  4. The Publish Skills workflow needs no change: v* still matches, the tag is only used as the GitHub release name, and the .skill filename strip targets the skill's SemVer in the filename, not the tag.

Read the full file on GitHub · 61 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. 5d ago First seen · 61 lines · 691 tokens per session scan A f63479ce2c73

Subscribe to this mod's changes

claude-skills AGENTS.md is an instructions file published in the GitHub repository obeone/claude-skills (3 stars, last pushed today), licensed MIT. It adds 691 tokens to every session, about $0.0035 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.