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/aliasunder/agent-skills/agents-mdgit clone --depth 1 https://github.com/aliasunder/agent-skillsWhat 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 | $0.00788 | $0.00788 |
| Opus 5 | $0.00394 | $0.00394 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
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 2d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
This file provides guidance to Claude Code (claude.ai/code), Codex CLI, and other AI agents when working with code in this repository.
Project Overview
agent-skills is a collection of agent skills — packaged instructions that extend AI coding agents with specialized capabilities. Install via npx skills add aliasunder/agent-skills.
Repository Structure
agent-skills/
README.md
CONTRIBUTING.md
LICENSE
package.json
skills/
<skill-name>/
SKILL.md # Skill definition (frontmatter: name, description)
references/ # Detailed reference docs loaded on demand
assets/ # Static files (dashboards, templates)
evals/
<skill-name>/ # Test scenarios and results
.github/workflows/
auto_release.yml # Tag-triggered build + GitHub release
manual_release.yml # UI-triggered version bump + release
Current Skills
| Skill | Directory | Description |
|---|---|---|
| Trip Planner | skills/trip-planner/ |
Multi-week trip planning across 15+ sessions with cross-validated research, budget tracking, printable daily cards, and phase-based workflow |
| Obsidian Vault | skills/obsidian-vault/ |
Vault-aware editing for Obsidian. Detects conventions, understands Dataview, Tasks, Kanban, Meta Bind, and Templater interactions, and keeps notes connected, queryable, and safe. |
Skill Architecture
Skills are discovered by npx skills scanning skills/*/SKILL.md. Each SKILL.md has YAML frontmatter with:
name— must match parent directory, lowercase letters/numbers/hyphensdescription— explains what the skill does and when it should activate
The body contains the operational instructions: workflow steps, conventions, reference file loading triggers, and safe output rules.
Reference files (references/*.md) are loaded on demand — only when the agent enters a task that needs them. This keeps the core SKILL.md lean while having deep guidance available.
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.
- 2d ago First seen · 78 lines · 788 tokens per session scan A be737a7280c1
agent-skills AGENTS.md is an instructions file published in the GitHub repository aliasunder/agent-skills (4 stars, last pushed 5d ago), licensed MIT. It adds 788 tokens to every session, about $0.0039 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
apm architecture.instructions.md
Single canonical owner discipline: one authority per durable decision, guarded by a regression test + a static boundary check.
apm python.instructions.md
Python development guidelines.
Awesome-Prompt-Engineering contribution-review.instructions.md
Instructions for natnew/Awesome-Prompt-Engineering, covering reviewing pull requests and issues, tone, how to respond, explaining quality concerns and maintainer judgement.
agent-skills AGENTS.md
Instructions for simota/agent-skills, covering agents.md — claude-skills, repository purpose, language policy, repository structure and skill authoring conventions.
loadout shell.instructions.md
Shell Script Engineering Instructions (Bash, CLI wrappers, automation).
skillkit CLAUDE.md
Instructions for maxvaega/skillkit, covering skillkit, development approach, current focus (v0.4), key architectural decisions and core architecture (v0.1).