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/yorrick/agent-skills/agents-mdgit clone --depth 1 https://github.com/yorrick/agent-skillsWrote 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.
[](https://agentmods.dev/instructions/yorrick/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/yorrick/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/yorrick/agent-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01373 | $0.01373 |
| Opus 5 | $0.00687 | $0.00687 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
agent-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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Agent skills and plugins for both Claude Code and Codex.
CLAUDE.md is a symlink to this file, so there is one set of instructions and it cannot
drift between harnesses.
The rule that matters
skills/<name>/SKILL.md and references/ are shared verbatim between harnesses —
Codex adopted the same format. The JSON manifests are generated from each plugin's
plugin.toml; never hand-edit a plugin.json or marketplace.json. After changing any
plugin.toml:
uv run scripts/sync_manifests.py
CI fails if the generated files drift. This is not theoretical: before the generator
existed, the marketplace advertised [email protected] while the plugin was 0.29.0.
The two manifests are not identical. Claude Code discovers skills/ and commands/
by convention; the Codex manifest declares them explicitly ("skills": "./skills/"),
matching what OpenAI's own manifests do rather than relying on fallback behaviour.
Plugin layout
<plugin>/
├── plugin.toml ← the ONLY file you hand-edit
├── skills/<name>/
│ ├── SKILL.md ← shared
│ ├── references/ ← optional, shared
│ └── agents/openai.yaml ← optional Codex interface and policy
├── commands/ ← optional, shared
├── hooks/ ← optional, shared
├── .claude-plugin/plugin.json ← generated
└── .codex-plugin/plugin.json ← generated
Marketplace manifests: .claude-plugin/marketplace.json (Claude Code — Codex reads it as
a legacy path) and .agents/plugins/marketplace.json (Codex canonical). Both generated.
Code quality
- Ruff for formatting and linting, pyright for type checking.
- These run automatically via PostToolUse hook on every Edit/Write of a Python file.
- To run manually:
uv run ruff check .anduv run pyright. - All Python scripts must use
uv run --scriptwith inline dependency metadata (PEP 723).
Validation checklist (every change)
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.
- yesterday Changed · +2 lines · +45 tokens per session 508047c17e20
- 5d ago First seen · 129 lines · 1,328 tokens per session scan A cdbc53959c25
agent-skills AGENTS.md is an instructions file published in the GitHub repository yorrick/agent-skills (10 stars, last pushed yesterday), licensed MIT. It adds 1,373 tokens to every session, about $0.0069 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.
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).
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.
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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.