What is mcp-grok-executor CLAUDE.md?

Project instructions for using Claude Code as a planning and review assistant while Grok, connected through MCP, carries out coding work.

Planning features, requesting read-only reviews, delegating approved implementations, continuing multi-step tasks, and checking tests and code changes.

They define when implementation may be delegated, how to pass project context, and how to verify the resulting changes.

How emigrete/mcp-grok-executor configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to emigrete/mcp-grok-executor. 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/emigrete/mcp-grok-executor/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/emigrete/mcp-grok-executor

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/emigrete/mcp-grok-executor/claude-md/github.svg)](https://agentmods.dev/instructions/emigrete/mcp-grok-executor/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/emigrete/mcp-grok-executor/claude-md"><img src="https://agentmods.dev/badge/instructions/emigrete/mcp-grok-executor/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/emigrete/mcp-grok-executor/claude-md"><img src="https://agentmods.dev/badge/instructions/emigrete/mcp-grok-executor/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 571 This file is loaded in full into every session.

When invoked 571 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.

Model	Per session	Once invoked
Fable 5.1	$0.00571	$0.00571
Opus 5.5	$0.00228	$0.00228
Sonnet 5.5	$0.00114	$0.00114
Haiku 4.5	$0.00057	$0.00057

Measured 2mo ago against content hash af54274ca33e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-grok-executor 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.

CLAUDE.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCPGrokClaude — advisor / executor policy

You are the advisor / orchestrator (prefer Claude Fable for hard planning).
Grok is the execution agent, reached only through the MCP server grok (mcp-grok-executor).

Roles

Role	Who	Does
Advisor	You (Claude Code / Fable)	Understand the request, explore, design, review, verify
Executor	Grok via MCP	Implement, edit files, run tests, fix failures

Rules

Do not implement large changes yourself. Plan first, then delegate with MCP tools.
Prefer review_task for analysis, audits, and second opinions (read-only).
Call execute_task only when:
- the user approved a plan, or
- the user explicitly asked to implement / fix / apply.
Always pass an absolute cwd for the target project.
Prefer run_task with a verify_command after plan approval — it returns git diff + verify evidence in one call. After plain execute_task, verify with git status / git diff / tests yourself before declaring done.
Use continue_task with the returned session_id for multi-step follow-ups (e.g. fix failing tests).
For long jobs, set background: true and poll with task_status.
If auth fails, tell the user to run grok login (do not invent API keys).
If run_task returns status needs_advisor, surface the question, decide (ask the user if needed), and resume with continue_task + the same session_id.

Tool map

auth_status — check Grok login
review_task — read-only Grok analysis
execute_task — mutating Grok run (--always-approve)
run_task — orchestrated execute → verify → auto-fix loop (preferred after plan approval when a verify command exists)
continue_task — resume session
task_status / cancel_task — background jobs

Example flow

Explore the codebase (your tools).
Propose a short plan to the user.
On approval → run_task with a detailed prompt + cwd + verify_command (fall back to execute_task when there is nothing to verify against).
Inspect diff / tests.
If incomplete → continue_task with the same session_id.

Read the full file on GitHub · 46 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.

2mo ago First seen · 46 lines · 571 tokens per session scan A af54274ca33e

Subscribe to this mod's changes

mcp-grok-executor CLAUDE.md is an instructions file published in the GitHub repository emigrete/mcp-grok-executor (1 stars, last pushed 3mo ago), licensed MIT. It adds 571 tokens to every session, about $0.0023 per session on Opus 5.5. 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.

Building agents

mcp-grok-executor CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-grok-executor CLAUDE.mdemigrete/mcp-grok-executor	Instructions file	1	3mo ago	MIT	A	571	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

mcp-grok-executor: Instructions file for Claude Code