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/ibook000/ibook-skill/claude-mdgit clone --depth 1 https://github.com/Ibook000/ibook-skillWrote 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/ibook000/ibook-skill/claude-md)<a href="https://agentmods.dev/instructions/ibook000/ibook-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/ibook000/ibook-skill/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 | $0.01317 | $0.01317 |
| Opus 5 | $0.00659 | $0.00659 |
| Sonnet 5 | $0.00263 | $0.00263 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
ibook-skill 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 — 107 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.
What This Repository Is
A skill registry — a collection of independent, self-contained AI agent skills for Claude Code, OpenClaw, and Codex. Each skill is a markdown-based persona/workflow definition that causes an AI agent to adopt specific behavioral patterns. This is not a traditional software project; the primary artifacts are .md files, not code.
Skills
| Skill | Location | Domain |
|---|---|---|
ibook-builder |
SKILL.md (root) |
Engineering builder persona — system-building, closed-loop delivery |
jiaoyiyuan-tony |
skills/jiaoyiyuan-tony/SKILL.md |
Trading discipline, risk control, position sizing |
tweet-card-generator |
skills/tweet-card-generator/SKILL.md |
Twitter data card generation with 12 chart types |
ssh-skill |
skills/ssh-skill/SKILL.md |
High-performance SSH operations with persistent connections and batch concurrency |
ioc-edit |
skills/ioc-edit/SKILL.md |
STM32CubeMX .ioc file editing (pins, peripherals, clocks, interrupts) |
image-well |
skills/image-well/SKILL.md |
Parallel image search across 12 APIs (4 no-key sources) |
chart-visualization |
skills/chart-visualization/SKILL.md |
Data visualization with 26 chart types |
notion-skill |
skills/notion-skill/SKILL.md |
Notion workspace operations |
xiaohongshu-finance |
skills/xiaohongshu-finance/SKILL.md |
Xiaohongshu financial content generation with banned-word avoidance |
Skill Anatomy (Convention for Adding/Editing Skills)
Every skill follows this structure:
SKILL.md— Core definition. YAML frontmatter (name,description), activation rules, behavioral protocols, output contracts, anti-patterns. This is what gets loaded into an AI agent's context.README.md— Human-readable docs: what it does, installation, usage examples.references/(optional) — Domain knowledge loaded at generation time (e.g., banned-word lists, reference guides).templates/(optional) — Reusable assets (HTML templates, shell scripts).examples/(optional) — Example configurations demonstrating usage.
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 · 107 lines · 1,317 tokens per session scan A 26584c12c01d
ibook-skill CLAUDE.md is an instructions file published in the GitHub repository Ibook000/ibook-skill (2 stars, last pushed 5d ago), licensed MIT. It adds 1,317 tokens to every session, about $0.0066 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
mspm0-skill AGENTS.md
Instructions for mc3545dada/mspm0-skill, covering repository agent instructions, repository rules, validation and documentation.
rk-skills CLAUDE.md
Claude Code instructions for richkuo/rk-skills, covering global guidelines, integrity (top priority, overrides every rule below), response style (every response), who you're working with and package manager.
mspm0-skill CLAUDE.md
Instructions for mc3545dada/mspm0-skill, a project described as: 面向电赛的 MSPM0 + SysConfig Agent Skill.
skul CLAUDE.md
Claude Code instructions for sjquant/skul, covering commands and ci checks.
rk-skills AGENTS.md
AGENTS.md instructions for richkuo/rk-skills, a project described as: Claude Code workflow skills — GitHub issue/PR/release automation and Fable-driven planning. Install via npx or as a Claude Code plugin.
skul AGENTS.md
AGENTS.md instructions for sjquant/skul, a project described as: Manage project-scoped personal AI configuration bundles (skills, commands, agents) for AI coding tools while supporting both stealth (git-excluded) and tracked installation, with full support for Git worktrees.