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.
npx agentmods add instructions/neptaco/mcproc/claude-mdgit clone --depth 1 https://github.com/neptaco/mcprocWhat 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 | $0.03910 | $0.03910 |
| Opus 5 | $0.01955 | $0.01955 |
| Sonnet 5 | $0.00782 | $0.00782 |
| Haiku 4.5 | $0.00391 | $0.00391 |
Grade A, and why
mcproc 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 440 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.
Project Overview
mcproc is a Rust-based daemon that fulfills Model Context Protocol (MCP) tool calls from LLMs and manages multiple development processes. The project provides a robust process management system with comprehensive logging, validation, and monitoring capabilities.
Key Architecture Components
High-Level Architecture
Claude / Other LLMs
│ JSON-RPC 2.0 (MCP) via stdio
▼
┌───────────────────────────────┐
│ mcproc (CLI + MCP server) │
│───────────────────────────────│
│ • MCP Tool Handlers │
│ • gRPC Client │
└───────────────────────────────┘
│ gRPC (Unix Domain Socket)
▼
┌───────────────────────────────┐
│ mcproc daemon (--daemon) │
│───────────────────────────────│
│ • Process Manager │
│ • Log Hub (direct file I/O) │
│ • gRPC API (tonic) │
└───────────────────────────────┘
│ stdout/stderr capture
▼
┌────────────────────────────────┐
│ Child Processes │
│ (npm run dev, python app.py, │
│ cargo run, etc.) │
└────────────────────────────────┘
Core Components
-
mcproc daemon: The main daemon process (runs as
mcproc --daemon)- Process Manager for spawning/managing child processes
- Log Hub with file-based logging (temporary, deleted on system reboot)
- API Layer using tonic (gRPC via Unix Domain Socket)
- Port detection and monitoring
- Process state tracking (Starting, Running, Stopping, Stopped, Failed)
-
mcproc: CLI tool for interacting with the daemon
- Communicates via gRPC Unix socket
- Supports commands: start, stop, restart, ps, logs, grep, clean, mcp serve
- Project-based process organization
- Auto-starts daemon if not running
-
mcp-rs: Reusable MCP library
- ServerBuilder for creating MCP servers
- Transport implementations (stdio implemented, SSE/HTTP planned)
- Tool registry and handler interfaces
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.
- 2d ago First seen · 440 lines · 3,910 tokens per session scan A 3c7f7aac4bb7
mcproc CLAUDE.md is an instructions file published in the GitHub repository neptaco/mcproc (10 stars, last pushed 9d ago), licensed MIT. It adds 3,910 tokens to every session, about $0.0196 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.
Other instructions, from other repositories
memorix CLAUDE.md
Instructions for AVIDS2/memorix, covering memorix - agent instructions for claude code, using memorix memory tools, when to search memory, when to store memory and when to resolve memory.
memorix GEMINI.md
Instructions for AVIDS2/memorix, covering memorix - cross-agent memory rules, session start - bind project, then load context, during session - capture important context, architecture & decisions and bug fixes & problem solving.
rosetta AGENTS.md
Instructions for griddynamics/rosetta: Main goal: cover E2E AI PDLC engineering workflows at foundation level for AI-First SDLC in enterprise. Top-level or orchestrator agents MUST READ docs/ARCHITECTURE.md contains technical details and guidance, and docs/CONTEXT.md - business context. Subagents - when needed.…
Chaterm CLAUDE.md
Claude Code instructions for chaterm/Chaterm, covering claude.md, project overview, core architecture, development commands and behavioral rules.
toon-memory AGENTS.md
Instructions for LuiggiVal08/toon-memory, covering agents.md, build & verify, architecture, smarter memory pattern and visual memory pattern.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.