Borrowing it
Nothing to install: this file belongs to andrewii23/ii23-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andrewii23/ii23-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/andrewii23/ii23-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/andrewii23/ii23-skills/claude-md)<a href="https://agentmods.dev/instructions/andrewii23/ii23-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/andrewii23/ii23-skills/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/andrewii23/ii23-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/andrewii23/ii23-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00400 | $0.00400 |
| Opus 5 | $0.00200 | $0.00200 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
ii23-skills 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 11d 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.
What it actually says
Each skill lives at skills/<name>/ with a SKILL.md and, where it needs them,
a scripts/ folder. Scripts are stdlib-only Python so a skill installs by
copying a folder.
Adding, renaming, or removing a skill means updating three places, or the repo starts lying about itself:
README.md— a problem-and-fix section under "Why these exist", plus a row in the Skills table. Every mention links to the skill'sSKILL.md.skills.sh.json— the skill's name in a grouping'sskillsarray.docs/<name>.md— the human-facing page. Follow .agents/writing-docs.md; a rename moves the file.
SKILL.md is the agent contract: what to run, in what order, and the traps to
avoid while doing it. It is not the place for the reasoning behind a decision.
That goes in .agents/adr/, and a rejected approach goes in .out-of-scope/
with the measurement that killed it — so nobody re-proposes it and no agent
burns a session rediscovering it.
Numbers in any document are measured, never estimated. Every performance claim in this repo came from a real run on a real file; if you change a claim, re-run the measurement first and say what you ran it on.
Validate a skill after editing it:
python3 ~/.agents/skills/skill-creator/scripts/quick_validate.py skills/<name>
Frontmatter limits it enforces: name <= 64 chars, description <= 1024. The
description is what makes a skill trigger, so it carries the trigger phrases
(including Thai ones) and an explicit "do NOT use for ..." boundary.
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.
- 11d ago First seen · 33 lines · 400 tokens per session scan A 74562c3dde9c
ii23-skills CLAUDE.md is an instructions file published in the GitHub repository andrewii23/ii23-skills (10 stars, last pushed 29d ago), licensed MIT. It adds 400 tokens to every session, about $0.0020 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
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.
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 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.
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.