A workflow for launching groups of headless Grok command-line workers, meaning Grok processes that run without an interactive screen. It prepares separate tasks and checks whether the environment is ready before starting them.

Running parallel research across files or folders and independent bite-sized implementation tasks with Grok workers. It also defines worker prompts, preflight checks, and fallback behavior when launching is unsuitable.

It helps divide suitable read-only research or small build tasks across workers while avoiding shared-process conflicts. The main session remains responsible for reviewing results and handling Git operations.

grok-spawn — Skill by jl-cmd

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 skills/jl-cmd/claude-dev-env/grok-spawn

Any agent

npx skills add jl-cmd/claude-dev-env --skill grok-spawn

Clone the repo

git clone --depth 1 https://github.com/jl-cmd/claude-dev-env

Made for: Claude Code, Codex.

Or install claude-dev-env, the plugin that ships this one along with the rest of its 45 skills, 9 agents, 1 hook.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,066 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00053	$0.02066
Opus 5	$0.00026	$0.01033
Sonnet 5	$0.00011	$0.00413
Haiku 4.5	$0.00005	$0.00207

Measured 3d ago against content hash fd579fb3112b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grok-spawn 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 3d 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.

packages/claude-dev-env/.agents/skills/grok-spawn/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grok Spawn

Orchestrator playbook for fleets of headless grok CLI workers. This skill names the scripts and the brief templates; it holds no spawn logic of its own.

Gotchas

Workers never commit, push, or call gh. The calling session stages, verifies, commits, pushes, and posts to GitHub.
Grok has no SendMessage and no Claude Agent tool. Work that needs live teammate chat or Claude-only tools stays in this session or a Claude agent.
Each worker gets its own --leader-socket. Sharing one socket across processes races and fails.
Preflight is a soft gate: a fallthrough reason means skip the fleet and use the next tier, not a hard crash of the whole run.
Prompt parts are plain files. Conversation-relative phrases ("as above") mean nothing to a headless worker — every brief stands alone.
spawn_grok_batch.py re-runs preflight before launch. An early preflight call still helps you abort before writing the batch spec.

When this skill applies

Use when the user asks for a grok worker fleet, a headless grok batch, or types /grok-spawn.

Good fits:

Fan-out read-only research across several paths or files
Parallel bite-sized build work where each worker owns a closed scope

Do not use when the work needs:

Live SendMessage coordination between agents
Claude-only tools (Agent tool, warm session-advisor, Claude MCP surfaces the grok CLI does not load the same way)

For a single interactive Grok Build handoff paste, use /grokify instead.

Refusal: no concrete worker tasks — reply What should the grok workers do? List each role in one line. and stop.

Process

Copy this checklist and check items off as you go.

[ ] 1. Preflight (#96 soft gate)
[ ] 2. Write prompt-part files (briefs + report contract)
[ ] 3. Write the batch JSON spec
[ ] 4. Run spawn_grok_batch.py
[ ] 5. Read the batch summary and per-worker reports
[ ] 6. Verify, then own every git and gh step yourself

1. Preflight

Scripts ship under $HOME/.claude/scripts/ after install (or the package scripts/ tree in this repo).

Read the full file on GitHub · 239 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago First seen · 239 lines · 53 tokens per session scan A fd579fb3112b

Subscribe to this mod's changes

grok-spawn is a skill published in the GitHub repository jl-cmd/claude-dev-env (6 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 2,066 once invoked, about $0.0003 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.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens