agentmods.dev

skills AGENTS.md

Project instructions for a Markdown-first collection of skills for AI coding agents. They define the required file format, description limits, registration process, and documentation restrictions.

In plain words
What is it for?
Use them when creating, editing, registering, or publishing a skill in this collection.
Why use it?
They prevent skills from being skipped during registration or breaking tools that render or load the Markdown files.

Instructions file for CodexOpenCode

3 13d ago A scan 222 tokens original MIT
View the source file mryll/skills
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/mryll/skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/mryll/skills

Made for: Codex, OpenCode.

Per session 222 This file is loaded in full into every session.
When invoked 222 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 $0.00222 $0.00222
Opus 5 $0.00111 $0.00111
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured 2d ago against content hash 3e4a0bc9391d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

AGENTS.md · 17 lines

What it actually says

AGENTS.md

Markdown-first skills collection — no build, tests, or linters. Skills may ship small helper scripts under skills/<name>/scripts/.

Skill File Format

  • Each skill lives at skills/<name>/SKILL.md with YAML frontmatter (name, description, version).
  • description MUST be a single-line string — never a YAML block scalar (| or >); block scalars break skill registration.
  • Keep description ≤1024 chars, or Codex CLI silently skips the skill.
  • Optional references/ subdirectory for supporting docs, linked from SKILL.md.

Non-Obvious Rules

  • Keep skills self-contained: each SKILL.md must work standalone, with no dependency on other skills.
  • Register every new skill in .claude-plugin/marketplace.json (the skills array) or it won't be published.
  • The skills.sh renderer crashes on Markdown tables and zero-width-char fence hacks in SKILL.md — use bullet lists and 4-backtick outer fences instead.
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. 2d ago First seen · 17 lines · 222 tokens per session scan A 3e4a0bc9391d

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository mryll/skills (3 stars, last pushed 13d ago), licensed MIT. It adds 222 tokens to every session, about $0.0011 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.

Building agentsagent-skillsagents-mdclaude-codecognitive-complexitygemini-cliprompt-engineering
Related

Other instructions, from other repositories

boring-is-all-you-need AGENTS.md

Instructions for Khalilzhang0825/boring-is-all-you-need, covering agents.md - boring is all you need codex guide, project intent, working rules, validation and release discipline.

Khalilzhang0825/boring-is-all-you-need · 422 tokens

AGENTS.md AGENTS.md

Instructions for Anbeeld/AGENTS.md, covering global instructions, priorities, boundaries, uncertainty and evidence.

Anbeeld/AGENTS.md · 1,964 tokens

agent-operating-protocol AGENTS.md

Instructions for ryu-tada/agent-operating-protocol, covering agents.md - agent operating protocol, 0. instruction priority and trust boundaries, 1. core operating stance, 2. why high-agency agents feel strong and 3. default work loop.

ryu-tada/agent-operating-protocol · 2,467 tokens

trellis AGENTS.md

Instructions for craigcossairt/trellis, covering agents.md , project, what i need from agents, current state - source of truth pointers and tech stack.

craigcossairt/trellis · 3,686 tokens

hames AGENTS.md

Instructions for baek-labs/hames, covering entry redirect, ⚠ mandatory enforcement, codex 전용 보충, hard constraints (요약 — 상세는 harnessengineering.md) and 핸드오프 처리.

baek-labs/hames · 880 tokens

trellis CLAUDE.md

Instructions for craigcossairt/trellis, a project described as: The structure a project grows on: a free starter template for AI-assisted development. One AGENTS.md every tool reads (Claude Code, Cursor, Grok Build, Codex, Gemini CLI, Copilot), TDD + bug-fix methodology, secret guardrails, optional local knowledge…

craigcossairt/trellis · 134 tokens