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 skills/arthurkatcher/grok-delegate/delegate-runtimenpx skills add arthurkatcher/grok-delegate --skill delegate-runtimegit clone --depth 1 https://github.com/arthurkatcher/grok-delegateWhat 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 | $0.00019 | $0.00296 |
| Opus 5 | $0.00010 | $0.00148 |
| Sonnet 5 | $0.00004 | $0.00059 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
delegate-runtime 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.
What it actually says
grok-delegate runtime
Hosting
run_terminal_command({ background: true, timeout: 0 })
→ node $GROK_PLUGIN_ROOT/scripts/delegate-companion.mjs <claude|codex> --wait [flags] -- <action> "focus"
→ expand Grok task for live tools
→ cancel task → SIGTERM kills Claude/Codex process group
Always set timeout: 0 (or multi-hour) on the Grok background shell — default ~20s kills long delegates with cancel (SIGTERM).
Never poll companion status into chat. Put free text after --. Prefer --payload-file for messy paste. Prefer --cwd at a real project, not $HOME.
Engines
claude— RO prefers hermetic--barewhenANTHROPIC_API_KEYis set; Max/OAuth without a key auto-drops--bareso first launch works; rescue = file tools only (no Bash unless user opts in)codex— OS sandbox;--searchis a global flag beforeexec; auto--skip-git-repo-checkwhen cwd is not a git work tree
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 · 26 lines · 19 tokens per session scan A 9e99359d4d64
delegate-runtime is a skill published in the GitHub repository arthurkatcher/grok-delegate (13 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 296 once invoked, about $0.0001 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.
Other skills, from other repositories
code-walkthrough
与用户共同阅读 Neeko 代码，逐层讲解 Tauri 应用架构与跨端数据流。支持三域分层模式（Rust 后端 / React 前端 / 跨端桥接）和调用链追踪模式（含跨端追踪）。主动发现 dead code、设计偏差、类型不一致、迁移遗漏，但不修改代码。Use when user wants to walkthrough code, understand architecture, trace call chains, review a module's structure, or says "过代码" / "walkthrough" / "walk me through" / "zoom out".
neeko-check
Neeko code review — 代码审核器，判定代码是否符合项目规范、业界 React/Rust 最佳实践与架构设计。用于提交前审查、PR 审查、或对指定代码进行规范审核。.
xterm-js
Expert guidance for building, configuring, and integrating xterm.js terminal emulators in web and Electron applications. Use this skill whenever the user mentions xterm, xterm.js, @xterm/xterm, terminal emulator in the browser, web terminal, WebSSH, in-browser shell, or asks about addons like FitAddon, WebglAddon…
html-effectiveness
Generate self-contained, interactive HTML documents instead of markdown walls of text. When output is complex (comparisons, timelines, multi-option decisions, data tables, code reviews, diagrams), produce a single .html file that renders spatially and interactively in the browser. Zero dependencies, zero build steps.…
rust-patterns
Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.