agentmods.dev

grok-delegate AGENTS.md

Repository instructions for grok-delegate, a Grok Build plugin that delegates tasks to Claude or Codex. They describe the project layout, commands, runtime, installation path, and rules for coding agents.

In plain words
What is it for?
They guide development, testing, installation, and maintenance of the grok-delegate plugin and its Node.js companion program.
Why use it?
They give agents the project’s exact structure and working rules, including that the repository root is a marketplace and the plugin lives in a subdirectory. This helps prevent edits or installation instructions in the wrong place.

Instructions file for CodexOpenCode

13 1mo ago A scan 908 tokens original MIT
View the source file arthurkatcher/grok-delegate
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/arthurkatcher/grok-delegate/agents-md
Clone the repo
git clone --depth 1 https://github.com/arthurkatcher/grok-delegate

Made for: Codex, OpenCode.

Per session 908 This file is loaded in full into every session.
When invoked 908 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 $0.00908 $0.00908
Opus 5 $0.00454 $0.00454
Sonnet 5 $0.00182 $0.00182
Haiku 4.5 $0.00091 $0.00091

Measured 2d ago against content hash 09b766dea328, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grok-delegate 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 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.

AGENTS.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — grok-delegate

Instructions for coding agents working in this repository.

What this repo is

Public GitHub marketplace Grok Build Extras for Grok Build. One plugin today:
Plugin grok-delegate
Path plugins/delegate/
Commands /delegate-claude, /delegate-codex
Runtime Node ESM companion under plugins/delegate/scripts/
Version 0.1.0 (MIT)

Clients install with:

grok plugin marketplace add arthurkatcher/grok-delegate
grok plugin install arthurkatcher/grok-delegate#plugins/delegate --trust

The #plugins/delegate subdir is required — repo root is the marketplace, not the plugin package.

Layout (do not invent a second one)

marketplace.json                 → Grok Build Extras catalog
plugins/delegate/
  .grok-plugin/plugin.json       → plugin manifest
  commands/                      → slash command markdown
  skills/delegate-runtime/       → how Grok must launch the companion
  scripts/delegate-companion.mjs → CLI entry
  scripts/lib/                   → args, policy, engines, stream, jobs, lifecycle
  tests/                         → unit + integration (node --test)
.github/workflows/ci.yml         → npm test + grok plugin validate
SECURITY.md · CHANGELOG.md · CONTRIBUTING.md · README.md

Non-negotiables

  1. Fail closed — unknown actions/flags exit non-zero; free text after -- cannot inject flags.
  2. Claude rescue = no Bash by default — file tools only; shell/git only via explicit --allowed-tools or --yolo.
  3. Read actions stay RO — Claude hermetic/dontAsk when API key is set; Max/OAuth without a key auto-drops --bare. Codex OS read-only unless user opts out; auto --skip-git-repo-check outside git.
  4. Preflight — every non-setup action checks binary + auth; same next steps as setup if not ready. Policy conflicts run before readiness.
  5. Host launch — Grok background task must use timeout: 0 (or very high); default ~20s cancels long runs.
  6. Cancel kills process group — do not regress child-lifecycle / SIGTERM on Grok task cancel.
  7. No secrets in git — no keys, tokens, job DBs, or real credentialed configs.
  8. Config vs product — this is a Grok plugin, not Meta MCP Manager; do not import meta-manager layout into this tree.

Read the full file on GitHub · 87 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. 2d ago First seen · 87 lines · 908 tokens per session scan A 09b766dea328

Subscribe to this mod's changes

grok-delegate AGENTS.md is an instructions file published in the GitHub repository arthurkatcher/grok-delegate (13 stars, last pushed 1mo ago), licensed MIT. It adds 908 tokens to every session, about $0.0045 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.

agentclaudeclaude-codecodexdeveloper-toolsgrok
Related

Other instructions, from other repositories

neeko AGENTS.md

Instructions for tincopper/neeko, covering neeko — repository guidelines, 项目概览, 目录结构, 前端（feature-based 架构） and 后端（domain-driven 模块化架构）.

tincopper/neeko · 7,575 tokens

neeko CLAUDE.md

Instructions for tincopper/neeko, covering neeko — claude.md, 项目概览, 常用命令速查, 键盘快捷键 and 预置 agent & ide.

tincopper/neeko · 790 tokens

clique CLAUDE.md

Claude Code instructions for thejdubb02/clique, covering clique — standing rules, motion, looking at it, the api is the whole surface and releasing.

thejdubb02/clique · 1,982 tokens

grok-build-mcp AGENTS.md

AGENTS.md instructions for zai-one/grok-build-mcp, covering agents.md — grok-delegate / unofficial grok mcp, язык, typed tools vs navigator, откуда берётся корень and проект должен сам включить мост.

zai-one/grok-build-mcp · 8,461 tokens

ccteam AGENTS.md

Instructions for firstintent/ccteam, covering agents.md — ccteam 实现导引, 〇、架构总览(定向图;红线唯一清单 = §三), 一、需求与版本管理(两条来源,都住 gitignored docs-local/), 二、仓库内文档(只有用户面;架构与协议一律读代码) and 三、不可触碰的架构红线(唯一权威清单).

firstintent/ccteam · 7,450 tokens

grok-build-mcp CLAUDE.md

Claude Code instructions for zai-one/grok-build-mcp: Неофициальный MCP-мост к Grok CLI. Правила проекта живут в AGENTS.md — он импортируется ниже, отдельно открывать не нужно. Плюс skill grok-mcp как роутер по инструментам.

zai-one/grok-build-mcp · 66 tokens