claudemd SKILL.md skillA

claudemd from martineserios/thebrana is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add martineserios/thebrana/claudemd@git:20260610.c15894f

Pins git:20260610.c15894f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
martineserios/thebrana
Path
system/skills/claudemd/SKILL.md
Versions recorded
5
Latest version
git:20260610.c15894f, committed Jun 10, 2026
First version recorded
May 8, 2026
Size
11,176 bytes
Repository stars
3
License
MIT

Audit or generate a CLAUDE.md for any project. Natural companion to /brana:align — run audit after align on brownfield projects.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# claudemd — Audit or Generate CLAUDE.md

Two modes:
- **audit** (default if CLAUDE.md exists): Read existing file, flag bloat and misplaced content, propose a leaner version.
- **generate** (default if no CLAUDE.md): Interview the user and produce a lean CLAUDE.md from scratch.

## When to use

- User wants to create a CLAUDE.md for a new project
- Existing CLAUDE.md has grown bloated or Claude is ignoring parts of it
- User wants to know what belongs in CLAUDE.md vs rules/, skills/, or hooks/
- After `/brana:onboard` surfaces that no CLAUDE.md exists
- After `/brana:align` on brownfield projects — to clean up bloat from F2 appending.

---

## Mode routing

Parse the first argument:
- `audit` or `audit <path>` → run **Audit** flow
- `generate` or `generate <path>` → run **Generate** flow
- No argument → check if `./CLAUDE.md` or `./.claude/CLAUDE.md` exists → if yes, **Audit**; if no, **Generate**

---

# Audit Flow

## Step 1: READ

Read the CLAUDE.md at the given path (default: `./CLAUDE.md`, then `./.claude/CLAUDE.md`).
Also read any files it imports (`@path` syntax).
Note total line count.

## Step 2: CLASSIFY

For each line/block, classify into one of:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add martineserios/thebrana/claudemd@sha256:b645bdd3506418e6

The line at the top of this page pins the label git:20260610.c15894f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_g3crrh3abzg7tiny.svg)](https://markdownregistry.com/a/art_g3crrh3abzg7tiny)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between May 8, 2026 and Jun 10, 2026, about one every 8 days.

versioncommittedcommitsizeaudit
git:20260610.c15894f latest2026-06-10 c15894f 11,176 BA view · diff
git:20260610.be2a8522026-06-10 be2a852 1,017 BA view · diff
git:20260530.d997ea52026-05-30 d997ea5 836 BA view · diff
git:20260508.18255072026-05-08 1825507 838 BA view · diff
git:20260508.5ac55032026-05-08 5ac5503 754 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (11176 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

martineserios/thebrana · 3 stars · license MIT · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_g3crrh3abzg7tiny
GET https://markdownregistry.com/api/v1/resolve?ref=martineserios/thebrana/claudemd
GET https://markdownregistry.com/api/v1/blob/b645bdd3506418e6a4da91aaf5b397fef2a8826e63efd1cf2079a1e70a50b5fb

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from martineserios/thebrana

cold-start-problem SKILL.md skill
martineserios/thebrana · .agents/skills/cold-start-problem/SKILL.md · Start and scale networked products using Andrew Chen''s "The Cold Start Problem" framework for network effects. Use…
v1.2.0 · audit A · 3 stars
critical-thinking-logical-reasoning SKILL.md skill
martineserios/thebrana · .agents/skills/critical-thinking-logical-reasoning/SKILL.md · Critical thinking and logical reasoning analysis skills for when you are explicitly asked to critically analyse written…
git:20260615.d11a2d9 · audit A · 3 stars
decision-matrix SKILL.md skill
martineserios/thebrana · .agents/skills/decision-matrix/SKILL.md · Compares multiple named alternatives against weighted criteria to produce transparent, defensible choices with explicit…
git:20260615.d11a2d9 · audit A · 3 stars
domain-driven-design SKILL.md skill
martineserios/thebrana · .agents/skills/domain-driven-design/SKILL.md · DDD tactical patterns for complex business modeling including entities, value objects, aggregates, domain services…
v1.0.0 · audit A · 3 stars
first-principles SKILL.md skill
martineserios/thebrana · .agents/skills/first-principles/SKILL.md · Break down complex problems to their fundamental truths, then reason up from there. Master Aristotle's ancient method…
v1.0.0 · audit A · 3 stars
inversion SKILL.md skill
martineserios/thebrana · .agents/skills/inversion/SKILL.md · "Invert, always invert." Apply Carl Jacobi's mathematical principle and Charlie Munger's investing wisdom to solve…
v1.0.0 · audit A · 3 stars
jobs-to-be-done SKILL.md skill
martineserios/thebrana · .agents/skills/jobs-to-be-done/SKILL.md · Discover what customers truly need by analyzing the "job" they hire your product to do. Use when the user mentions…
v1.5.0 · audit A · 3 stars
marketplace-fundamentals SKILL.md skill
martineserios/thebrana · .agents/skills/marketplace-fundamentals/SKILL.md · Help users understand the core mechanics of marketplace businesses, from solving the cold start problem to maintaining…
git:20260731.0803ef5 · audit A · 3 stars
marketplace-liquidity-take-rates SKILL.md skill
martineserios/thebrana · .agents/skills/marketplace-liquidity-take-rates/SKILL.md · Help users define precise liquidity metrics, set competitive take rates based on value delivery, and manage the…
git:20260731.0803ef5 · audit A · 3 stars
pre-mortem SKILL.md skill
martineserios/thebrana · .agents/skills/pre-mortem/SKILL.md · Imagine your project has failed spectacularly—then work backward to identify why. Apply Gary Klein's "prospective…
v1.0.0 · audit A · 3 stars
second-order-thinking SKILL.md skill
martineserios/thebrana · .agents/skills/second-order-thinking/SKILL.md · Think beyond immediate consequences to understand the chain reactions of decisions. Master Howard Marks' investment…
v1.0.0 · audit A · 3 stars
six-thinking-hats SKILL.md skill
martineserios/thebrana · .agents/skills/six-thinking-hats/SKILL.md · Apply Edward de Bono's parallel thinking framework (1985) to make better decisions by examining ideas from six distinct…
v1.0.0 · audit A · 3 stars

Every file in martineserios/thebrana

Other files named claudemd

claudemd SKILL.md skill
anantys-oss/koan · koan/skills/core/claudemd/SKILL.md · Refresh or create CLAUDE.md for a project, or sync Kōan's learnings into it
v1.1.0 · audit A · 48 stars

Browse by kind, by grade A, or by owner.