agentmods.dev

code-reasoning: Instructions file for Claude Code

CLAUDE.md

code-reasoning CLAUDE.md is an instructions file for Claude Code from mettamatt/code-reasoning. It costs 440 tokens per session, scanned A, a copy of code-reasoning AGENTS.md, MIT.

Project instructions for Code Reasoning MCP, a TypeScript server that helps with structured reasoning for programming tasks.

In plain words
What is it for?
Use them when building, testing, formatting, linting, or extending the Code Reasoning MCP server and its tools.
Why use it?
They record the project's renamed components, supported configuration key, commands, naming conventions, module format, and type-safety expectations. This prevents changes from using outdated names or incompatible coding patterns.

Instructions file for Claude Code

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

This is mettamatt/code-reasoning's own configuration. It tells Claude Code how to work on code-reasoning 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 code-reasoning configures →

not rated 257repo +1 9mo ago A scan 440 tokens copy · 89% MIT archived
View source ↗ mettamatt/code-reasoning
Reuse

Borrowing it

Nothing to install: this file belongs to mettamatt/code-reasoning. 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/mettamatt/code-reasoning/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mettamatt/code-reasoning

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 code-reasoning CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mettamatt/code-reasoning/claude-md"><img src="https://agentmods.dev/badge/instructions/mettamatt/code-reasoning/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 440 This file is loaded in full into every session.
When invoked 440 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 89% 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 $0.00440 $0.00440
Opus 5.5 $0.00176 $0.00176
Sonnet 5.5 $0.00088 $0.00088
Haiku 4.5 $0.00044 $0.00044

Measured 2mo ago against content hash 85eb4a2154ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-reasoning 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 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.

Origin

This is a copy

89% identical to code-reasoning AGENTS.md — 4 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 · 37 lines

What it actually says

CLAUDE.md

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

Naming Convention Note

This project was originally forked from the Sequential Thinking MCP Server but has been renamed to Code Reasoning MCP Server to better reflect its specialized focus on programming tasks. The tool has been renamed from "sequentialthinking" to "code-reasoning" for consistency. All configuration must use "code-reasoning" as the key - the "sequential-thinking" configuration key is not supported. The class previously named "SequentialThinkingServer" has been renamed to "CodeReasoningServer" for consistency.

Build/Test/Lint Commands

  • Build: npm run build
  • Start: npm run start, npm run debug
  • Test: npm run test (runs ESLint)
  • Lint: npm run lint, npm run lint:fix
  • Format: npm run format, npm run format:check
  • Validation: npm run validate (runs format, lint:fix, and build)

Code Style Guidelines

  • Parameters: snake_case (e.g., thought_number, not thoughtNumber)
  • Imports: ES Modules with .js extension
  • Types: Strict TypeScript with explicit types; avoid any where possible
  • Error Handling: Use structured logging with Logger class
  • Logging: Use logger.error/info/debug instead of console.log
  • Formatting: Prettier with singleQuotes, tabWidth: 2, printWidth: 100
  • Variables: Use descriptive names, camelCase for variables/functions

Always run npm run lint and npm run format before committing changes.

Documentation Locations

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. 2mo ago First seen · 37 lines · 440 tokens per session scan A 85eb4a2154ee

Subscribe to this mod's changes

code-reasoning CLAUDE.md is an instructions file published in the GitHub repository mettamatt/code-reasoning (257 stars, last pushed 9mo ago), licensed MIT. It adds 440 tokens to every session, about $0.0018 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to code-reasoning AGENTS.md, differing in 4 lines, and is treated as a copy.

Related

code-reasoning CLAUDE.md compared with instructions from other repositories

code-reasoning CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
code-reasoning CLAUDE.mdmettamatt/code-reasoningInstructions file2579mo agoMITA440Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode