mcp-context-manager CLAUDE.md

mcp-context-manager CLAUDE.md is an instructions file for coding agents from transparentlyok/mcp-context-manager. It costs 933 tokens per session, scanned A, original, MIT.

A set of instructions for using MCP Context Manager, a tool system for searching and understanding code. It requires loading those tools and indexing the repository before code navigation.

In plain words
What is it for?
It guides conversations that involve locating functions, classes, symbols, or related code. It is for repositories connected to MCP Context Manager.
Why use it?
It prevents the agent from searching code before the required tools and repository index are ready. It also establishes a consistent way to find relevant code.

Instructions file

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.

agentmods
npx agentmods add instructions/transparentlyok/mcp-context-manager/claude-md
Clone the repo
git clone --depth 1 https://github.com/transparentlyok/mcp-context-manager

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-context-manager CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/transparentlyok/mcp-context-manager/claude-md.svg)](https://agentmods.dev/instructions/transparentlyok/mcp-context-manager/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/transparentlyok/mcp-context-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/transparentlyok/mcp-context-manager/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 933 This file is loaded in full into every session.
When invoked 933 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00933 $0.00933
Opus 5 $0.00466 $0.00466
Sonnet 5 $0.00187 $0.00187
Haiku 4.5 $0.00093 $0.00093

Measured 5d ago against content hash e09a4b82aa5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-context-manager 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 5d 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 · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Context Manager - Developer Guide

⚠️ CRITICAL: MANDATORY Tool Loading Process

This project provides MCP (Model Context Protocol) tools for intelligent code navigation.

STEP 1: Load MCP Tools FIRST (Required)

At the START of EVERY conversation involving code search/navigation:

ToolSearch query: "select:mcp__context-manager__index_repository,mcp__context-manager__get_relevant_context,mcp__context-manager__find_symbol,mcp__context-manager__get_function"

DO NOT skip this step. MCP tools are deferred and must be explicitly loaded before use.

STEP 2: Index Repository (If Not Already Indexed)

mcp__context-manager__index_repository

Only after these steps can you use MCP tools.

❌ DO NOT Use Built-in Tools Without MCP First

FORBIDDEN workflow:

  1. User asks question
  2. You immediately use Grep/Read/Glob
  3. ❌ WRONG - you skipped loading MCP tools

CORRECT workflow:

  1. User asks question
  2. Load MCP tools via ToolSearch
  3. Use index_repository if needed
  4. Use get_relevant_context or other MCP tools
  5. ✅ CORRECT

When to Use MCP Tools

ALWAYS prefer MCP tools over Read/Grep/Glob for:

  • Finding functions, classes, or symbols
  • Understanding code structure
  • Searching for specific functionality
  • Navigating large codebases
  • Getting file summaries

Available MCP Tools (After Loading)

Tool Use Instead Of Benefit
get_relevant_context Grep + Read multiple files 70-90% token savings
find_symbol Grep for function/class names Fuzzy matching, exact locations
get_function Read entire file for one function Returns only the function code
get_class Read entire file for one class Returns only the class definition
search_code Grep with regex Ranked results, better formatting
find_similar Manual code comparison Automatic similarity scoring
get_file_summary Read for quick overview Structure only, no implementation
get_repository_structure ls/tree commands Clean hierarchy, no noise
get_dependencies Manual import tracing Automatic dependency graph

Read the full file on GitHub · 123 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. 5d ago First seen · 123 lines · 933 tokens per session scan A e09a4b82aa5b

Subscribe to this mod's changes

mcp-context-manager CLAUDE.md is an instructions file published in the GitHub repository transparentlyok/mcp-context-manager (13 stars, last pushed 3mo ago), licensed MIT. It adds 933 tokens to every session, about $0.0047 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 2026-08-30.

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 · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 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

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 · 3,733 tokens