A tool for creating or improving CLAUDE.md files, which are instruction files that tell Claude how to work in a codebase. It can analyze the project, document its structure and conventions, or audit an existing file and apply focused updates.

Use it to generate a new CLAUDE.md, review and improve an existing one, or maintain project guidance for future coding sessions.

It saves developers from manually inspecting the repository and maintaining these instructions as the project changes. It also helps capture build, testing, naming, architecture, and deployment practices in one place.

claude-md — Skill for Claude Code by hamzaPixl

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 hamzaPixl/pixl-ai --skill claude-md

Clone the repo

git clone --depth 1 https://github.com/hamzaPixl/pixl-ai

Made for: Claude Code.

Or install pixl-crew, the plugin that ships this one along with the rest of its 93 skills, 14 agents, 6 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/claude-md/github.svg)](https://agentmods.dev/skills/hamzapixl/pixl-ai/claude-md)

Your own site

<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/claude-md"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/claude-md"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,124 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found 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.

Model	Per session	Once invoked
Fable 5.1	$0.00079	$0.01124
Opus 5	$0.00039	$0.00562
Sonnet 5	$0.00016	$0.00225
Haiku 4.5	$0.00008	$0.00112

Measured 12d ago against content hash 0621cb5da737, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

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 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.

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.

packages/crew/skills/claude-md/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md Manager

Unified skill for creating and maintaining CLAUDE.md files. Replaces the separate claude-md-generator and claude-md-improver skills.

Mode Detection

Argument	Mode
`generate` or no existing CLAUDE.md	Generate from scratch
`improve` or existing CLAUDE.md found	Audit and improve
No argument	Auto-detect based on CLAUDE.md presence

Mode A: Generate

Create a CLAUDE.md by analyzing the codebase.

Step 1: Scan (Parallel — 3 Agents)

Spawn 3 Explore agents to scan in parallel:

Agent A: Project structure, directories, key files, build system
Agent B: Code patterns, naming conventions, architecture
Agent C: Testing patterns, CI/CD, deployment

Step 2: Analyze

Identify the project type (library, service, monorepo, CLI)
Map the tech stack (language, framework, build tools)
Extract common patterns (file naming, directory structure, imports)
Identify testing framework and conventions

Step 3: Extract Conventions

Extract coding standards from existing code
Identify error handling patterns
Map dependency injection or configuration patterns
Note security practices and authentication patterns
Identify deployment and infrastructure patterns

Step 4: Assemble

Generate CLAUDE.md with sections:

Project Overview — What it is, tech stack, key commands
Architecture — Directory structure, key modules, data flow
Conventions — Naming, file structure, import order, error handling
Development — How to run, test, build, deploy
Patterns — Specific patterns to follow when contributing

Check examples/ directory for project-type-specific templates.

Mode B: Improve

Audit and improve existing CLAUDE.md files.

Phase 1: Discovery

Find all CLAUDE.md files:

find . -name "CLAUDE.md" -o -name ".claude.md" -o -name ".claude.local.md" 2>/dev/null | head -50

File Types:

Type	Location	Purpose
Project root	`./CLAUDE.md`	Primary project context (shared)
Local overrides	`./.claude.local.md`	Personal settings (gitignored)
Global defaults	`~/.claude/CLAUDE.md`	User-wide defaults
Package-specific	`./packages/*/CLAUDE.md`	Module-level in monorepos

Read the full file on GitHub · 142 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.

12d ago First seen · 142 lines · 79 tokens per session scan A 0621cb5da737

Subscribe to this mod's changes

claude-md is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 5mo ago), licensed MIT. It adds 79 tokens to every session and 1,124 once invoked, about $0.0004 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.

Building agents Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens