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/meteor/agent-skills/agents-mdgit clone --depth 1 https://github.com/meteor/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/meteor/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/meteor/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/meteor/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 | $0.02994 | $0.02994 |
| Opus 5 | $0.01497 | $0.01497 |
| Sonnet 5 | $0.00599 | $0.00599 |
| Haiku 4.5 | $0.00299 | $0.00299 |
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 4d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring an Agent Skill for meteor/agent-skills
This document is the contract for everyone writing a skill in this repo. Plan 01 created it; subsequent plans must not break it without updating it here first.
Maintainer skills
Repository maintenance workflows live under .github/skills/. They help contributors maintain the published catalog but are not included in release ZIPs or the README catalog.
| Skill | Use when |
|---|---|
skill-maintenance |
Creating, reviewing, or updating a published skill while preserving repository conventions. |
skill-gap-audit |
Comparing Meteor documentation and source changes with current skill coverage. |
release-publishing |
Preparing, testing, tagging, or publishing beta and stable plugin releases. |
Audit and maintenance workflow
skill-gap-audit is read-only by default. It produces an evidence-backed report and does not change published skills. Confirmed findings move to skill-maintenance only when the user requests implementation.
skill-gap-audit
-> confirmed findings
-> authorized implementation scope
-> skill-maintenance
-> affected manual cases when routing or high-risk guidance changes
-> repository validation
-> release ZIP verification
When one request explicitly asks to audit and fix, complete the audit first, preserve its evidence, then load skill-maintenance and implement only confirmed findings within the requested scope. Do not implement uncertain findings or create proposed skills without explicit user approval.
pnpm run validate enforces frontmatter, naming, body size, prohibited-content rules, required evaluation-case files, plugin packaging consistency, and required revision and handoff fields in committed gap-audit reports. pnpm run check-links checks links in published and maintainer skills. The ZIP test suite verifies that .github/skills/ and repository maintenance evidence remain outside release artifacts.
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.
- 4d ago First seen · 242 lines · 2,994 tokens per session scan A e2bfa0003d07
agent-skills AGENTS.md is an instructions file published in the GitHub repository meteor/agent-skills (7 stars, last pushed 7d ago), licensed MIT. It adds 2,994 tokens to every session, about $0.0150 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.
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.