ai-md

ai-md is a skill for Claude Code, Codex from pinkpixel-dev/skills-collection-1. It costs 33 tokens per session (4,927 once invoked), scanned B, a copy of ai-md, Apache-2.0.

A method for rewriting human-written instructions for AI systems into a structured format with labels. It can be applied to files such as CLAUDE.md, which store project rules for an AI coding assistant.

In plain words
What is it for?
Use it to convert project instructions, reduce unnecessary prompt length, move rules between AI tools, or reorganize system instructions for clearer compliance.
Why use it?
Long prose instructions can be easy for an AI system to overlook and expensive to repeat. The structured format keeps the same rules more organized and aims to improve how consistently they are followed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Codex.

Good fit Use it to convert project instructions, reduce unnecessary prompt length, move rules between AI tools, or reorganize system instructions for clearer compliance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pinkpixel-dev/skills-collection-1/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 pinkpixel-dev/skills-collection-1 --skill ai-md
Clone the repo
git clone --depth 1 https://github.com/pinkpixel-dev/skills-collection-1

Made for: Claude Code, Codex.

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/pinkpixel-dev/skills-collection-1/ai-md/github.svg)](https://agentmods.dev/skills/pinkpixel-dev/skills-collection-1/ai-md)
Your own site
<a href="https://agentmods.dev/skills/pinkpixel-dev/skills-collection-1/ai-md"><img src="https://agentmods.dev/badge/skills/pinkpixel-dev/skills-collection-1/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/pinkpixel-dev/skills-collection-1/ai-md"><img src="https://agentmods.dev/badge/skills/pinkpixel-dev/skills-collection-1/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 9d ago against content hash 8ece61e4b20f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

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. 9d 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 pinkpixel-dev/skills-collection-1 (7 stars, last pushed 1mo ago), licensed Apache-2.0. 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

security-compliance

Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.

sangrokjung/claude-forge · 56 tokens

ai-policy-generator

AI governance policy creation for nonprofits and enterprises with frameworks, risk assessment, ethical guidelines, and compliance templates. Use when drafting AI usage policies, responsible AI frameworks, or organizational AI governance documents.

travisjneuman/.claude · 42 tokens

compliance-engineering

SOC2, HIPAA, GDPR, PCI-DSS, FedRAMP compliance implementation in code. Audit logging, data encryption, access controls, privacy by design, and regulatory requirement mapping. Use when implementing compliance controls, preparing for audits, or building privacy-compliant systems.

travisjneuman/.claude · 60 tokens

anonymization-alternative

Evaluates anonymization as a retention alternative under GDPR Recital 26, applying the WP29 Opinion 05/2014 techniques including randomization and generalization. Validates anonymization effectiveness using k-anonymity, l-diversity, and t-closeness metrics. Activate for anonymization, de-identification, k-anonymity…

onfire7777/universal-ai-skills-library · 80 tokens

bcr-establishment

Guides development and approval of Binding Corporate Rules under GDPR Article 47 for intra-group international data transfers. Covers Art. 47(2)(a)-(n) content requirements, BCR approval process with lead supervisory authority, and WP256/WP257 referentials. Keywords: BCR, binding corporate rules, intra-group…

onfire7777/universal-ai-skills-library · 77 tokens

legal-contract-reviewer

Plain-language contract summary, clause-risk table, and questions to ask a lawyer. Analysis only — NOT legal advice.

conectlens/lenserfight · 28 tokens