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/btreemap/skills/agents-mdgit clone --depth 1 https://github.com/BTreeMap/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/btreemap/skills/agents-md)<a href="https://agentmods.dev/instructions/btreemap/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/btreemap/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 | $0.04338 | $0.04338 |
| Opus 5 | $0.02169 | $0.02169 |
| Sonnet 5 | $0.00868 | $0.00868 |
| Haiku 4.5 | $0.00434 | $0.00434 |
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 today.
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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository is a central, project-agnostic library of reusable agent skills.
Each skill is a self-contained SKILL.md describing a procedure an LLM agent can
load and execute. Downstream projects consume it as a git submodule mounted at
.github/skills, as a Claude Code plugin, or through a skills manager such as
npx skills, so every skill here MUST be neutral and reusable across
unrelated projects. Load linked skills only when a task needs them.
Repository shape
- One directory per skill, named in kebab-case, containing a file named exactly
SKILL.md. The directory name MUST match the skill'snamein its frontmatter. - Naming convention: a task skill is an imperative verb phrase, the command a
user would speak (
fact-check,read-pdf,git-commit); a persona or stance skill is a single noun (caveman,ponytail,pl-theorist). No filler nouns (-protocol,-helper,-skills), no gerunds. - Every top-level directory that is neither dotted nor
skills/IS a skill directory; that namespace is reserved. Repository plumbing lives in dotted directories (.github,.claude,.claude-plugin) or in single files at the root (e.g.sync-skills.example.yml). skills/is the vendor-neutral hub: one committed relative symlink per skill,skills/<skill-name>to../<skill-name>. Every vendor path is one symlink to that hub, so another agent costs one link..github/skillsserves GitHub Copilot and mirrors the path downstream projects mount this repository at;.claude/skillsserves Claude Code..claude-plugin/carries the installer manifests:marketplace.jsonlists every skill by its canonical root path, the address installers resolve, andplugin.jsondeclares the same root container to Claude Code. The gate regenerates that list from the tree, so adding a skill never edits a manifest by hand.LICENSE: MIT.- This repository is documentation that other agents read; correctness is an
editorial property. The exception is the bundled Python, a uv workspace: the
root
pyproject.tomllists every member,uv.lockpins the whole library, and the gate lints, formats, and tests it (see Automated gate).
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.
- today Changed · -109 lines · -1,586 tokens per session ae434eaf71a0
- 4d ago First seen · 425 lines · 5,924 tokens per session scan A cf6b7ae045c8
SKILLs AGENTS.md is an instructions file published in the GitHub repository BTreeMap/SKILLs (2 stars, last pushed yesterday), licensed MIT. It adds 4,338 tokens to every session, about $0.0217 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.