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/hk-hub/agentskills/claude-mdgit clone --depth 1 https://github.com/HK-hub/AgentSkillsWrote 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/hk-hub/agentskills/claude-md)<a href="https://agentmods.dev/instructions/hk-hub/agentskills/claude-md"><img src="https://agentmods.dev/badge/instructions/hk-hub/agentskills/claude-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 5.1 | $0.00852 | $0.00852 |
| Opus 5 | $0.00426 | $0.00426 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
AgentSkills CLAUDE.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 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.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository purpose
This repository is a curated skills collection for Claude Code/agents.
It is not a single deployable application. Most top-level directories are standalone skills with their own SKILL.md and optional support files.
High-level architecture
1) Skill-oriented monorepo layout
Typical unit:
<skill-name>/
├── SKILL.md # Required entrypoint and trigger description
├── references/ # Deep docs loaded on demand
├── scripts/ # Utilities used by the skill
├── examples/ # Usage examples
└── assets/ # Output templates/resources
2) No root build/test pipeline
There is no root package.json, pyproject.toml, or CI workflow in this repo root.
Development/validation commands are skill-specific and must be run in the relevant skill context.
3) Content-first + script-assisted design
Most skills are instruction-heavy (SKILL.md) with optional deterministic helpers under scripts/.
When editing, preserve the relationship between trigger metadata (frontmatter), workflow body, and referenced resources.
Common commands used in this repo
Run these from the proper directory for each skill.
Agent Development
bash "Agent Development/scripts/validate-agent.sh" <path-to-agent.md>
web-artifacts-builder
bash scripts/init-artifact.sh <project-name>
bash scripts/bundle-artifact.sh
webapp-testing
python scripts/with_server.py --server "npm run dev" --port 5173 -- python your_automation.py
readme-generate
python readme-generate/scripts/readme_generator.py <spring-module-path>
skill-creator
python -m scripts.aggregate_benchmark <workspace>/iteration-N --skill-name <name>
python -m scripts.run_loop --eval-set <eval.json> --skill-path <skill-path> --model <model-id> --max-iterations 5 --verbose
python -m scripts.package_skill <path/to/skill-folder>
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 · 96 lines · 852 tokens per session scan A e13507639c32
AgentSkills CLAUDE.md is an instructions file published in the GitHub repository HK-hub/AgentSkills (6 stars, last pushed 18d ago), licensed MIT. It adds 852 tokens to every session, about $0.0043 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
rp1 AGENTS.md
Instructions for rp1-run/rp1, covering rp1 agent authoring guide, core rules, namespace prefixes, subagent limitations and codex task shorthand.
minimax-h3-opencode-skills AGENTS.md
Instructions for unknowlei/minimax-h3-opencode-skills, covering ai installation contract, install target, required installation and safety.
rp1 CLAUDE.md
Instructions for rp1-run/rp1, covering commit discipline, 1up — agent quick reference, tool selection, setup and commands.
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.