What is claude-md-writer?

A tool for writing and reviewing CLAUDE.md files, which give Claude Code project instructions. It focuses on concise sections, instruction priority, and avoiding repeated guidance.

Use it to create or improve global, project-level, or local CLAUDE.md files and decide which guidance belongs in each one.

It helps keep these always-loaded instruction files short and clear, so they use less context and are easier for the agent to follow.

claude-md-writer — Skill for Claude Code by anilcancakir

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 anilcancakir/claude-code-plugin --skill claude-md-writer

Clone the repo

git clone --depth 1 https://github.com/anilcancakir/claude-code-plugin

Made for: Claude Code.

Or install ac, the plugin that ships this one along with the rest of its 6 skills, 9 commands, 2 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/anilcancakir/claude-code-plugin/claude-md-writer.svg)](https://agentmods.dev/skills/anilcancakir/claude-code-plugin/claude-md-writer)

Your own site

<a href="https://agentmods.dev/skills/anilcancakir/claude-code-plugin/claude-md-writer"><img src="https://agentmods.dev/badge/skills/anilcancakir/claude-code-plugin/claude-md-writer.svg" alt="Measured on agentmods" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,298 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	$0.00059	$0.02298
Opus 5	$0.00030	$0.01149
Sonnet 5	$0.00012	$0.00460
Haiku 4.5	$0.00006	$0.00230

Measured 8d ago against content hash 5e42341cf5a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-md-writer 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 8d 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/ac/skills/claude-md-writer/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md Writer

Write CLAUDE.md files that Claude Code actually follows. Every line must earn its place — CLAUDE.md loads every conversation turn, consuming context window tokens each time.

How CC Loads CLAUDE.md

CLAUDE.md is delivered as a user message after the system prompt — advisory context, not enforced configuration. Adherence degrades with file length and conflicting rules.

Loading order (lowest → highest priority):

Managed policy (/Library/Application Support/ClaudeCode/CLAUDE.md) — org-wide, cannot exclude
User global (~/.claude/CLAUDE.md + ~/.claude/rules/)
Project walkup — from working dir upward: ./CLAUDE.md + ./.claude/CLAUDE.md + ./.claude/rules/ at each level
Local (./CLAUDE.local.md) — personal, not git-tracked
Additional dirs (via CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD env var)

Subdirectory CLAUDE.md files lazy-load when Claude touches files in that directory.

Compaction: CLAUDE.md survives /compact — re-read from disk and re-injected. Conversation-only instructions are lost.

Import syntax: @path/to/file pulls in additional files. Max 5 hops. Relative paths resolve from the importing file.

Size Limits

File	Target	Hard limit
Global `~/.claude/CLAUDE.md`	≤120 lines	40K chars (CC warning)
Project `./CLAUDE.md`	≤120 lines (~2500 tokens)	40K chars (CC warning)
`CLAUDE.local.md`	≤50 lines	Same
`MEMORY.md`	≤200 lines or 25KB	Hard truncation

Shorter files = better adherence. Over 200 lines, instruction-following drops measurably.

Core Principles

Compression-first: Every token costs every turn. One-liner per concept when possible
Non-obvious only: If Claude can infer it from reading code, don't state it
Actionable: Commands copy-paste-ready, paths real, steps concrete
Project-specific: Generic advice ("write tests", "use meaningful names") is noise
Dedup-aware: Don't repeat what CC system prompt or higher-level CLAUDE.md already provides

Read the full file on GitHub · 228 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

8d ago First seen · 228 lines · 59 tokens per session scan A 5e42341cf5a0

Subscribe to this mod's changes

claude-md-writer is a skill published in the GitHub repository anilcancakir/claude-code-plugin (2 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 2,298 once invoked, about $0.0003 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 Claude Code Multi-Agent Orchestration Writing and docs development-twin plan-first

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

claude-md-writer