reforge-mcp: Instructions file for Claude Code

CLAUDE.md

reforge-mcp CLAUDE.md is an instructions file for Claude Code from Codewithaiyan/reforge-mcp. It costs 1,820 tokens per session, scanned A, a copy of wick CLAUDE.md, MIT.

Project instructions for a codebase that contains a generated knowledge graph. They tell Claude Code which graph reports and commands to use when answering code questions.

In plain words
What is it for?
Use them in a project with a graphify knowledge graph to guide architecture research, cross-module questions, and graph updates.
Why use it?
They give the coding agent a consistent way to understand the project structure instead of scanning unrelated files. They also keep the graph updated after code changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Codewithaiyan/reforge-mcp's own configuration. It tells Claude Code how to work on reforge-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything reforge-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Codewithaiyan/reforge-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/Codewithaiyan/reforge-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Codewithaiyan/reforge-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.

agentmods badge for reforge-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/codewithaiyan/reforge-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/codewithaiyan/reforge-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/codewithaiyan/reforge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/codewithaiyan/reforge-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.

agentmods 80×15 button for reforge-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/codewithaiyan/reforge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/codewithaiyan/reforge-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,820 This file is loaded in full into every session.
When invoked 1,820 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 100% copy Near-identical to another mod 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01820 $0.01820
Opus 5.5 $0.00728 $0.00728
Sonnet 5.5 $0.00364 $0.00364
Haiku 4.5 $0.00182 $0.00182

Measured yesterday against content hash 00fce56d6c6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reforge-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 yesterday.

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.

Origin

This is a copy

100% identical to wick CLAUDE.md — 130 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for working in this repository.

What this is

An MCP server that exposes a codebase to Claude Code as structured tools so it can scan, plan and apply refactors with rollback. Python 3.11+, tree-sitter for parsing, FastMCP for the tool surface. Pre-1.0 and honestly alpha.

Commands

uv run pytest -q            # the test suite — plain `python -m pytest` has no pytest installed
uv run pytest tests/test_fix.py -q
uv run reforge-mcp          # start the server (stdio)

Self-scan — the fastest way to see whether a scanner change actually works:

uv run python -c "import sys,json; sys.path.insert(0,'src'); \
from reforge_mcp.tools.scan import scan_repo; \
print(json.dumps(scan_repo('.'), indent=1))"

Layout

src/reforge_mcp/
  server.py          FastMCP entry point — registers all tools, thin wrappers only
  tools/             one file per MCP tool: scan, chunk, fix, git
  scanner/           analysis: parser (tree-sitter), dead_code, duplicates, risk, architecture
  scanner/adapters/  per-language stubs (currently 7 lines each; see R20)
  utils/             security (path + command validation), diff, state
tests/               one file per module, pytest, no fixtures framework beyond tmp_path

Invariants — do not break these

  • Every path from a tool argument goes through utils.security.validate_path before any read or write. It is the only thing standing between a caller and the rest of the filesystem. Same for validate_test_command before any subprocess.
  • server.py stays thin. Tool functions there wrap an implementation in tools/ or scanner/ and do nothing else. Logic in server.py is untestable.
  • State writes are .tmp -> rename. See utils/state.py:save_state. Never write reforge-state.json in place.
  • write_fix must leave the file either correctly changed or byte-identical, on every path. The backup is a byte copy under a unique tempfile name, so restoring it is a no-op even where nothing needed restoring; if a new early-return is added, check it goes through _restore or unlinks the copy. Never read or write a patched file with read_text/write_text: that translates line endings and was R37.
  • Scanner output is a public contract. scan_repo's return shape is consumed by get_health_score, score_risk and infer_architecture. Changing a key means changing all three.

Read the full file on GitHub · 140 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.

  1. yesterday Changed · +20 lines · +314 tokens per session 00fce56d6c6b
  2. 6d ago Changed · +110 lines · +1,352 tokens per session d027d2d1b38c
  3. 2mo ago First seen · 10 lines · 154 tokens per session scan A 6f25c42ffb3c

Subscribe to this mod's changes

reforge-mcp CLAUDE.md is an instructions file published in the GitHub repository Codewithaiyan/reforge-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 1,820 tokens to every session, about $0.0073 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to wick CLAUDE.md, differing in 130 lines, and is treated as a copy.

Related

Other instructions, from other repositories

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 · 9,715 tokens

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 · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens