What is claude-md-conventions?

A guide for creating or updating CLAUDE.md files, which give Claude Code project-specific instructions. It defines the sections for project context, build commands, architecture, and repository conventions.

Use it when adding repository guidance, documenting build and test commands, explaining project structure, or generating instructions with an initialization command.

It helps keep agent instructions useful, consistent, and focused on information that is not obvious from the code.

claude-md-conventions — Skill for Claude Code by metaschema-framework

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 metaschema-framework/claude-plugins --skill claude-md-conventions

Clone the repo

git clone --depth 1 https://github.com/metaschema-framework/claude-plugins

Made for: Claude Code.

Or install dev-metaschema, the plugin that ships this one along with the rest of its 7 skills, 3 commands.

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/metaschema-framework/claude-plugins/claude-md-conventions/github.svg)](https://agentmods.dev/skills/metaschema-framework/claude-plugins/claude-md-conventions)

Your own site

<a href="https://agentmods.dev/skills/metaschema-framework/claude-plugins/claude-md-conventions"><img src="https://agentmods.dev/badge/skills/metaschema-framework/claude-plugins/claude-md-conventions/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/metaschema-framework/claude-plugins/claude-md-conventions"><img src="https://agentmods.dev/badge/skills/metaschema-framework/claude-plugins/claude-md-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,240 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	$0.00034	$0.01240
Opus 5.5	$0.00014	$0.00496
Sonnet 5.5	$0.00007	$0.00248
Haiku 4.5	$0.00003	$0.00124

Measured 2mo ago against content hash d458ae8646ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-md-conventions 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 2mo 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.

plugins/dev-metaschema/skills/claude-md-conventions/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md Conventions

When to Use

Creating a new CLAUDE.md for a repository
Updating existing CLAUDE.md content
Running /init command to generate CLAUDE.md

Purpose of CLAUDE.md

CLAUDE.md provides guidance to Claude Code when working in a repository. It should contain:

Project-specific information that Claude needs to work effectively
Non-obvious conventions that aren't discoverable from code
Commands for building, testing, and quality checks
Architecture overview for quick orientation

Required Sections

1. Header

# CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

2. Overview (Brief)

One paragraph describing:

What the project does
Key technologies or frameworks
Any domain-specific context needed

3. Build Commands

Essential commands grouped logically:

## Build Commands

\`\`\`bash
# Build all modules
mvn install

# CI build (required before pushing)
mvn install -PCI -Prelease

# Run tests
mvn test

# Run single test
mvn -pl module test -Dtest=TestClass#testMethod
\`\`\`

4. Project Architecture

Brief module/package overview. Use text language identifier for ASCII diagrams:

## Project Architecture

\`\`\`text
project-root
├── module-a  - Description
├── module-b  - Description
└── module-c  - Description
\`\`\`

5. Key Conventions (Blocking Items)

Document conventions that must be followed, marked as BLOCKING:

## Code Style

- **Javadoc**: 100% coverage on public/protected (BLOCKING)
- **TDD**: Tests must be written first (BLOCKING)

## Git Workflow

- **All PRs MUST target `develop` branch** (BLOCKING)
- **All PRs MUST be from personal fork** (BLOCKING)

6. Available Skills

Reference skills from installed plugins:

## Available Skills

### Development (dev-metaschema plugin)
- `dev-metaschema:development-workflow` - TDD, debugging, PRD workflow
- `dev-metaschema:javadoc-style-guide` - Javadoc requirements and patterns

Read the full file on GitHub · 236 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.

2mo ago First seen · 236 lines · 34 tokens per session scan A d458ae8646ae

Subscribe to this mod's changes

claude-md-conventions is a skill published in the GitHub repository metaschema-framework/claude-plugins (10 stars, last pushed 8mo ago), licensed CC0-1.0. It adds 34 tokens to every session and 1,240 once invoked, about $0.0001 per session on Opus 5.5. 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.

Writing and docs

claude-md-conventions next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-md-conventionsmetaschema-framework/claude-plugins	Skill	10	8mo ago	CC0-1.0	A	34	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	3d ago	MIT	A	200	Claude Code, Codex
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	315k	6d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code