What is write-like-me-mcp CLAUDE.md?

Project instructions for the write-like-me-mcp codebase, including its design, file responsibilities, conventions, and privacy requirements.

Use them when developing or reviewing write-like-me-mcp.

They give coding agents the context needed to change the project without breaking its local-only data handling.

How gwicho38/write-like-me-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to gwicho38/write-like-me-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/gwicho38/write-like-me-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/gwicho38/write-like-me-mcp

Made for: Claude Code.

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/instructions/gwicho38/write-like-me-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/gwicho38/write-like-me-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/gwicho38/write-like-me-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gwicho38/write-like-me-mcp/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/instructions/gwicho38/write-like-me-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gwicho38/write-like-me-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,106 This file is loaded in full into every session.

When invoked 1,106 The same file — it is already loaded in full.

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	$0.01106	$0.01106
Opus 5	$0.00553	$0.00553
Sonnet 5	$0.00221	$0.00221
Haiku 4.5	$0.00111	$0.00111

Measured 9d ago against content hash d1ec54dceb91, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

write-like-me-mcp 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 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.

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.

CLAUDE.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — write-like-me-mcp

Project-specific instructions for Claude Code working in this repository.

What this project is

An MCP server that learns a user's personal writing style from a local document corpus and serves self-updating style context to Claude. The defining constraint is privacy: everything runs on-device, nothing crosses the network, and no verbatim corpus text is ever persisted or shipped. Treat that as the prime directive — any change that could leak private content or open a network edge is a bug, not a feature.

Architecture (where things live)

Module	Responsibility
`src/write_like_me_mcp/config.py`	Load/validate `write-like-me.json`, select active profile, resolve paths.
`src/write_like_me_mcp/model.py`	`StyleProfile` dataclass + `profile.json` (de)serialization.
`src/write_like_me_mcp/style_analyzer.py`	Compute style metrics + signature phrases from text.
`src/write_like_me_mcp/extractors.py`	Extract text from TXT/MD/PDF/DOCX/HTML.
`src/write_like_me_mcp/indexer.py`	SQLite FTS5 + BM25 excerpt index (`examples.db`).
`src/write_like_me_mcp/watcher.py`	Debounced watchdog corpus-change rebuilds.
`src/write_like_me_mcp/server.py`	FastMCP server, lifespan, the 5 tools.

Code conventions

These are enforced across the codebase — match them in any new code:

stderr-only logging. stdout is the MCP protocol channel. All diagnostic output goes through the module logger (configured to sys.stderr). Never print() to stdout and never reconfigure logging to stdout.
Pydantic inputs are strict. Every tool input model uses ConfigDict(str_strip_whitespace=True, extra="forbid") so unknown fields are rejected. Keep new tool inputs the same.
Tools return JSON strings. Tool functions return json.dumps(...) (with indent=2, ensure_ascii=False for human-readable payloads) — not dicts and not bare objects.
Named constants, no magic literals. Thresholds, filenames, env-var names, limits, and tolerances are module-level UPPER_SNAKE_CASE constants with a docstring/comment. Don't inline literals into logic.
Full type hints. Every function/method is fully annotated (params + return). from __future__ import annotations is at the top of each module. uv run mypy src must stay clean.
No hard-coded secrets or paths. No API keys, tokens, or absolute user paths (/Users/..., /home/..., C:\...) in committed source, config, or docs. Paths come from config/env and are resolved at runtime only; resolved absolute paths live solely on the in-memory StyleConfig and are never persisted or emitted (results use basenames / data-root-relative forms).

Read the full file on GitHub · 90 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.

9d ago First seen · 90 lines · 1,106 tokens per session scan A d1ec54dceb91

Subscribe to this mod's changes

write-like-me-mcp CLAUDE.md is an instructions file published in the GitHub repository gwicho38/write-like-me-mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 1,106 tokens to every session, about $0.0055 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

write-like-me-mcp: Instructions file for Claude Code