ai-md

ai-md is a skill for Claude Code from lucaspmarie-a11y/claude-skills-vault. It costs 33 tokens per session (4,927 once invoked), scanned B, a copy of ai-md, MIT.

A method for rewriting human-written instructions for AI models into a compact format using structured labels. It is designed for CLAUDE.md files and other system prompts.

In plain words
What is it for?
Use it to convert project instructions, optimize long prompts, or move rules between AI tools such as Claude, Codex, Gemini, and Grok.
Why use it?
It aims to make rules easier for an AI model to follow while using fewer instruction tokens than verbose prose.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Codex.

Part of the antigravity-awesome-skills plugin — 199 skills shipped together

Good fit Use it to convert project instructions, optimize long prompts, or move rules between AI tools such as Claude, Codex, Gemini, and Grok.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lucaspmarie-a11y/claude-skills-vault/ai-md
Install

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.

Any agent
npx skills add lucaspmarie-a11y/claude-skills-vault --skill ai-md
Clone the repo
git clone --depth 1 https://github.com/lucaspmarie-a11y/claude-skills-vault

Made for: Claude Code.

Or install antigravity-awesome-skills, the plugin that ships this one along with the rest of its 199 skills.

Wrote 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.

agentmods badge for ai-md

README.md
[![agentmods](https://agentmods.dev/badge/skills/lucaspmarie-a11y/claude-skills-vault/ai-md/github.svg)](https://agentmods.dev/skills/lucaspmarie-a11y/claude-skills-vault/ai-md)
Your own site
<a href="https://agentmods.dev/skills/lucaspmarie-a11y/claude-skills-vault/ai-md"><img src="https://agentmods.dev/badge/skills/lucaspmarie-a11y/claude-skills-vault/ai-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.

agentmods 80×15 button for ai-md

Your own site · 80×15
<a href="https://agentmods.dev/skills/lucaspmarie-a11y/claude-skills-vault/ai-md"><img src="https://agentmods.dev/badge/skills/lucaspmarie-a11y/claude-skills-vault/ai-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,927 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 97% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.04927
Opus 5 $0.00016 $0.02464
Sonnet 5 $0.00007 $0.00985
Haiku 4.5 $0.00003 $0.00493

Measured 12d ago against content hash 8ece61e4b20f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

ai-md scanned grade B with 2 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 12d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

rules=$(cat ~/.claude/rules/*.md 2>/dev/null | wc -c || echo 0)

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

EVIDENCE: no-fabricate no-guess | 禁用詞:應該是/可能是 → 先拿數據 | Read/Grep→行號 curl→數據 | "好像"/"覺得"→自己先跑test | guess=shame-wall
Origin

This is a copy

97% identical to ai-md — 509 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/antigravity-awesome-skills-claude/skills/ai-md/SKILL.md · 519 lines

How it starts

The opening of the file, as written. The whole thing — 519 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI.MD v4 — The Complete AI-Native Conversion System

When to Use This Skill

  • Use when your CLAUDE.md is long but AI still ignores your rules
  • Use when token usage is too high from verbose system instructions
  • Use when you want to optimize any LLM system prompt for compliance
  • Use when migrating rules between AI tools (Claude, Codex, Gemini, Grok)

What Is AI.MD?

AI.MD is a methodology for converting human-written CLAUDE.md (or any LLM system instructions) into a structured-label format that AI models follow more reliably, using fewer tokens.

The paradox we proved: Adding more rules in natural language DECREASES compliance. Converting the same rules to structured format RESTORES and EXCEEDS it.

Human prose (6 rules, 1 line)  → AI follows 4 of them
Structured labels (6 rules, 6 lines) → AI follows all 6
Same content. Different format. Different results.

Why It Works: How LLMs Actually Process Instructions

LLMs don't "read" — they attend. Understanding this changes everything.

Mechanism 1: Attention Splitting

When multiple rules share one line, the model's attention distributes across all tokens equally. Each rule gets a fraction of the attention weight. Some rules get lost.

When each rule has its own line, the model processes it as a distinct unit. Full attention weight on each rule.

# ONE LINE = attention splits 5 ways (some rules drop to near-zero weight)
EVIDENCE: no-fabricate no-guess | 禁用詞:應該是/可能是 → 先拿數據 | Read/Grep→行號 curl→數據 | "好像"/"覺得"→自己先跑test | guess=shame-wall

# FIVE LINES = each rule gets full attention
EVIDENCE:
  core: no-fabricate | no-guess | unsure=say-so
  banned: 應該是/可能是/感覺是/推測 → 先拿數據
  proof: all-claims-need(data/line#/source) | Read/Grep→行號 | curl→數據
  hear-doubt: "好像"/"覺得" → self-test(curl/benchmark) → 禁反問user
  violation: guess → shame-wall

Mechanism 2: Zero-Inference Labels

Natural language forces the model to INFER meaning from context. Labels DECLARE meaning explicitly. No inference needed = no misinterpretation.

Read the full file on GitHub · 519 lines

Changes

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.

  1. 12d ago First seen · 519 lines · 33 tokens per session scan B 8ece61e4b20f

Subscribe to this mod's changes

ai-md is a skill published in the GitHub repository lucaspmarie-a11y/claude-skills-vault (5 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 4,927 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). It is 97% identical to ai-md, differing in 509 lines, and is treated as a copy.

Related

Other skills, from other repositories

llm-app-patterns

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

davila7/claude-code-templates · 54 tokens

prompt-optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…

langwatch/langwatch · 105 tokens

enhance-prompt

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

google-labs-code/stitch-skills · 41 tokens

prompt-engineer

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…

Jeffallan/claude-skills · 93 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.

Emily2040/seedance-2.0 · 61 tokens

ideogram4

Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…

digitalsamba/claude-code-video-toolkit · 99 tokens