mcp-chain: Instructions file for Claude Code

CLAUDE.md

mcp-chain CLAUDE.md is an instructions file for Claude Code from ruliana/mcp-chain. It costs 1,835 tokens per session, scanned A, original, MIT.

Instructions for using a TODO.md file as persistent working memory in an MCP-chain project. They describe how to initialize, plan, and update a multi-step task across sessions.

In plain words
What is it for?
Use them to create a task plan, track phases and sub-tasks, record problems, and maintain shared context in ai/TODO.md.
Why use it?
They help an agent preserve task context and avoid losing decisions, progress, or unresolved issues when work continues later.

Instructions file for Claude Code

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

This is ruliana/mcp-chain's own configuration. It tells Claude Code how to work on mcp-chain 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 mcp-chain configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ruliana/mcp-chain. 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/ruliana/mcp-chain/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ruliana/mcp-chain

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 mcp-chain CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ruliana/mcp-chain/claude-md"><img src="https://agentmods.dev/badge/instructions/ruliana/mcp-chain/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,835 This file is loaded in full into every session.
When invoked 1,835 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01835 $0.01835
Opus 5 $0.00918 $0.00918
Sonnet 5 $0.00367 $0.00367
Haiku 4.5 $0.00184 $0.00184

Measured 9d ago against content hash 8eeb55afb033, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-chain 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 · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

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

AI Memory Management with TODO.md

TODO.md as AI Memory System

The ai/TODO.md file serves as persistent memory for multi-phase tasks:

  • Cross-Session Context: Contains all context needed to continue tasks in new sessions
  • Living Document: You should actively update it while working
  • Problem Prevention: Record issues to avoid repeating mistakes
  • Phase-Based Structure: High-level phases with local planning
  • Learning Integration: Continuously improve based on experience

TODO Workflow for AI Assistants

1. Task Initialization

When user requests a multi-phase task:

# ALWAYS do this first for new long-term tasks
rm -f ai/TODO.md  # Remove existing TODO if present
cp ai/TODO_template.md ai/TODO.md  # Create new from template
# Then customize the template for the specific task
2. Phase Execution Pattern

MANDATORY: Create local plan before implementation

**Local Plan:** (Create detailed sub-tasks when starting this phase)
- [ ] Analyze current codebase structure
- [ ] Identify specific files to modify
- [ ] Create test cases for new functionality
- [ ] Implement core changes
- [ ] Validate implementation
3. Active Updates During Work

Update TODO.md frequently:

  • Mark completed sub-tasks with [x]
  • Record any problems encountered in "Problems Encountered & Solutions"
  • Update "Context for Next Session" before ending work
  • Document successful patterns that work well
  • Note any changes to approach or strategy
4. Session Handoff

Before ending each session:

  • Update "Current Status" and "Active Phase"
  • Fill in "Context for Next Session" with essential information
  • Record any unresolved issues in "Problems Encountered"
  • Update "Last Updated" timestamp

Template Usage Instructions

Creating New TODO from Template
  1. Replace Template Variables: All {VARIABLE_NAME} placeholders with actual values
  2. Customize Phases: Adjust phases to match your specific task requirements
  3. Set Context: Fill in project-specific commands and background information
  4. Initialize Status: Set current phase and status appropriately

Read the full file on GitHub · 214 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. 9d ago First seen · 214 lines · 1,835 tokens per session scan A 8eeb55afb033

Subscribe to this mod's changes

mcp-chain CLAUDE.md is an instructions file published in the GitHub repository ruliana/mcp-chain (7 stars, last pushed 1y ago), licensed MIT. It adds 1,835 tokens to every session, about $0.0092 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.

Related

Other instructions, from other repositories

repobrain copilot-instructions.md

Copilot instructions for study8677/repobrain, covering github copilot bootstrap instructions and hard rule — query the repobrain hub first.

study8677/repobrain · 229 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 · 7,296 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

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

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens