grok-build-mcp: Instructions file for Codex

AGENTS.md

grok-build-mcp AGENTS.md is an instructions file for Codex, OpenCode from zai-one/grok-build-mcp. It costs 8,461 tokens per session, scanned A, original, MIT.

Project instructions for an unofficial bridge that lets a host assistant such as Claude, Cursor, or Codex delegate work to Grok. They define language rules, tool choices, session handling, worktree use, and verification practices.

In plain words
What is it for?
For configuring the grok-delegate project, including Russian operator communication, session-based work, typed tools, temporary Git worktrees, and test verification.
Why use it?
They keep delegation predictable by separating Grok's worker role from the host assistant's coordinating and checking role.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Codex.

This is zai-one/grok-build-mcp's own configuration. It tells Codex and OpenCode how to work on grok-build-mcp 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 grok-build-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zai-one/grok-build-mcp. 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/zai-one/grok-build-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/zai-one/grok-build-mcp

Made for: Codex, OpenCode.

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 grok-build-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zai-one/grok-build-mcp/agents-md.svg)](https://agentmods.dev/instructions/zai-one/grok-build-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zai-one/grok-build-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/zai-one/grok-build-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,461 This file is loaded in full into every session.
When invoked 8,461 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 5.1 $0.08461 $0.08461
Opus 5 $0.04230 $0.04230
Sonnet 5 $0.01692 $0.01692
Haiku 4.5 $0.00846 $0.00846

Measured 5d ago against content hash af41aa6743ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

grok-build-mcp AGENTS.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.

AGENTS.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — grok-delegate / unofficial Grok MCP

Неофициальный мост. Не xAI / Grok. Цель: Grok = дешёвый worker, хост (Claude / Cursor / Codex) = оркестратор и verifier.

Текущий цикл: unpin CLI; валидные карточки session_next; bounded evidence pack; правила агентов; multi-version без пина.

Язык

Оператор проекта пишет по-русски — отвечать ему по-русски, включая объяснения, отчёты, вопросы и summary. Это правило, а не догадка по языку последнего сообщения: одна английская фраза от оператора его не отменяет.

Русский — язык общения с оператором и внутрипроектной документации (AGENTS.md, Service/Handoffs/*). Артефакты, которые читает не только оператор, остаются английскими:

Английский Русский
commit messages, ветки, теги ответы оператору в чате
код, идентификаторы, docstrings, комментарии AGENTS.md, handoff-и, evidence
README.md, CHANGELOG, GitHub Issue / PR операторские runbook-и и объяснения

Смешивать в одном артефакте не надо: файл либо русский, либо английский целиком.

Typed tools vs navigator

Путь Когда
Navigator: session_begin → loop session_nextsession_end Дешёвый цикл. Карточка grok_agent_execute = полный task; grok_agent_poll = только {job_id}.
Typed: consult → execute → poll → review Fallback, если карточка отвергнута / schema error / хост без navigator.

Хост не скармливает весь репозиторий в контекст. Читает compact receipt: changed_files, diffstat, bounded unified_diff, tests, worktree_path.

В tests попадает только прогон, который сделал сам мост (source: "bridge-verifier"). То, что о своих тестах сказал агент, помечено agent-reported и доказательством не считается: живой capture показал exit_code: 0 при упавшем pytest, потому что в цепочке a; b код возврата принадлежит последней команде. Verifier запускается независимо от того, доработал агент свой ход или упёрся в max_turns. Если tests пуст — tests_skipped_reason говорит почему (NO_CHANGES / NO_TEST_COMMANDS / CANCELLED / NOT_A_WRITE_ROLE), и пустой список больше не путается с «тесты не прогонялись».

Read the full file on GitHub · 251 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 · 251 lines · 8,461 tokens per session scan A af41aa6743ed

Subscribe to this mod's changes

grok-build-mcp AGENTS.md is an instructions file published in the GitHub repository zai-one/grok-build-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 8,461 tokens to every session, about $0.0423 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

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 · 5,182 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

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