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/peterhdd/agent-skills/agents-mdgit clone --depth 1 https://github.com/PeterHdd/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/peterhdd/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/peterhdd/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/peterhdd/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 | $0.00655 | $0.00655 |
| Opus 5 | $0.00328 | $0.00328 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00065 | $0.00065 |
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 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure
This repository is an engineering skills catalog for AI agent runtimes (Claude Code, Codex). Built to the Agent Skills Spec. Contains 9 engineering skills.
skills/<skill-id>/
├── SKILL.md # Decision rules and workflow (required)
├── references/ # Deep code patterns and examples
│ └── *.md
└── scripts/ # Runnable CLI tools (Python/Bash)
└── *.py / *.sh
skills/<skill-id>/SKILL.md: Core skill definition with decision rules, loaded by the agent automatically.skills/<skill-id>/references/: Detailed code examples and patterns that SKILL.md links to. Agent reads on demand.skills/<skill-id>/scripts/: Standalone CLI tools the agent can run during sessions. All support--helpand output markdown.scripts/validate-skills.sh: Validates all skills have correct frontmatter and structure.
No app runtime, package build, or test suite is included.
Commands
# Validate all skills
./scripts/validate-skills.sh --no-skills-ref
# Install skills
npx skills add PeterHdd/agent-skills --all
npx skills add PeterHdd/agent-skills --skill engineering-frontend-developer
Skill Authoring Rules
- Frontmatter in each
SKILL.mdmust include:name: <skill-id>(matches folder name)description: "when to use this skill"(this is the trigger — agents activate the skill based on this)metadata.version: x.y.z
- Skill folder names use lowercase kebab-case (e.g.,
engineering-frontend-developer). - SKILL.md should contain "when X, do Y" decision rules, not persona descriptions or job listings.
- Reference files go in
references/— SKILL.md links to them withSee [Name](references/file.md) for .... - Scripts must be self-contained (stdlib only), support
--help, and output structured markdown. - All scripts must be executable (
chmod +x). - No placeholders, no stubs, no "implement here" comments in any file.
Pre-PR Checklist
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 · 61 lines · 655 tokens per session scan A 89615bdea038
agent-skills AGENTS.md is an instructions file published in the GitHub repository PeterHdd/agent-skills (11 stars, last pushed 5mo ago), licensed MIT. It adds 655 tokens to every session, about $0.0033 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 2026-08-30.
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.
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.