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/tmchow/agent-skills/agents-mdgit clone --depth 1 https://github.com/tmchow/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/tmchow/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/tmchow/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/tmchow/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 | $0.03581 | $0.03581 |
| Opus 5 | $0.01791 | $0.01791 |
| Sonnet 5 | $0.00716 | $0.00716 |
| Haiku 4.5 | $0.00358 | $0.00358 |
Grade A, and why
agent-skills AGENTS.md scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl/wget interpolation), not a `printf` redirect in docs. The consent How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-skills
A personal, multi-skill collection of cross-platform AI agent skills
(SKILL.md format), installable à la carte through runtime-specific lanes:
the generic skills CLI (npx skills add tmchow/agent-skills --skill <name>,
works across Claude Code/Cursor/Codex and other Agent-Skills runtimes), Hermes
(GitHub directory identifiers via hermes skills install owner/repo/path/to/skill
or /skills install owner/repo/path/to/skill; raw SKILL.md URLs are valid only
for single-file fallback installs), and OpenClaw (ClawHub via
openclaw skills install <slug>). The Hermes path segment is the exact skill
directory relative to repo root — do not add skills/ unless the skill actually
lives under a skills/ directory. Document lanes side by side; never present
one as the only path.
This guide is for anyone (human or agent) editing the repo. Keep it accurate when conventions change.
Repo layout
Every top-level directory is a skill, identified by a SKILL.md inside it
— with one exception: _assets/. That's the rule installers use (they
find skills by looking for SKILL.md), so anything that isn't a skill must
not look like one at the root.
<skill-name>/SKILL.md— required. The agent-facing instructions.<skill-name>/README.md— required. The human-facing landing page (below).<skill-name>/references/— optional. Deep material loaded on demand._assets/<skill-name>/— optional. Docs-only images a skill links by raw URL (calibration examples, README embeds). Two reasons it lives here, not in the skill dir: installers copy the entire skill directory verbatim, so anything inside ships to every user; and the leading_is an impossible skill-name start ([a-z0-9-]), so it can never be mistaken for a skill. Namespace by skill so it scales without cluttering the root.- Root
README.md— the catalog: one row per skill. - Root
LICENSE— MIT.
Adding or editing a skill
- Directory name == the skill's
name:frontmatter, lowercase kebab-case ([a-z0-9-], no leading/trailing/double hyphens, 1–64 chars). - Write
SKILL.md(frontmatter + body rules below). - Write
README.md(human landing page — rules below). - Put deep or optional material in
references/, not inSKILL.md. - Add a one-line row to the root
README.mdskill table. - Validate (below) before committing.
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.
- 5d ago First seen · 265 lines · 3,581 tokens per session scan A 91be41560f64
agent-skills AGENTS.md is an instructions file published in the GitHub repository tmchow/agent-skills (64 stars, last pushed 19d ago), licensed MIT. It adds 3,581 tokens to every session, about $0.0179 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.