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/skymavis/skills/agents-mdgit clone --depth 1 https://github.com/skymavis/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/skymavis/skills/agents-md)<a href="https://agentmods.dev/instructions/skymavis/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/skymavis/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 | $0.00803 | $0.00803 |
| Opus 5 | $0.00402 | $0.00402 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
skills AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — the skills repo
You are an agent authoring and maintaining reusable agent skills in this repo. This file governs
how to work here; each skill's own SKILL.md governs how to use that skill.
Read order (every task)
- This file.
README.md— the catalog and layout.scripts/validate_skills.py— the contract you must satisfy.CONTRIBUTING.md— the authoring workflow and local dev loop.- The target skill's
SKILL.md.
The skill contract (self-check before running the validator)
- A skill is a folder
skills/<name>/containing aSKILL.md. - Folder name == frontmatter
name, kebab-case^[a-z0-9-]+$, ≤ 64 chars, no leading/trailing/consecutive hyphen, and notanthropic/claude. - Frontmatter is a top-of-file YAML block fenced by
---…---. Allowed keys only:name,description,license,allowed-tools,metadata,compatibility.nameanddescriptionare required. description: non-empty, ≤ 1024 chars, third person, no angle brackets. It is the trigger surface — say what the skill does and when to use it.SKILL.mdbody ≤ 500 lines (budget). Push depth intoreferences/.- Relative links in
SKILL.mdmust resolve.
Authoring discipline
- Each skill is self-contained under
skills/<name>/:scripts/(executable logic),references/(depth loaded on demand),assets/(templates/files the skill emits),tests/(pytest, with aconftest.pythat injectsscripts/ontosys.path). - Prefer the standard library; declare any extra test deps in the skill's
requirements-dev.txt(CI always installspytest). - Progressive disclosure: keep
SKILL.mdlean; depth goes inreferences/. - Don't hand-format
SKILL.mdline shape.pre-commitrunsmdformat --wrap 100over everySKILL.md, so write prose in whatever line shape and let the hook reflow it (it leaves tables, code blocks, and long URLs intact). Runpre-commit run --all-filesand commit the result; CI checks the same fixed point.
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.
- 3d ago First seen · 56 lines · 803 tokens per session scan A be338e9a854b
skills AGENTS.md is an instructions file published in the GitHub repository skymavis/skills (0 stars, last pushed 3d ago), licensed MIT. It adds 803 tokens to every session, about $0.0040 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 2026-09-01.
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.
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.
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).
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.