A worker-agent guide for sending repetitive or narrowly defined coding tasks to Grok Build, while Claude or a person reviews the results.

Use it for tasks such as adding missing tests, applying migrations, generating boilerplate, or making mechanical refactors.

It sets boundaries for delegating low-risk volume work and prevents unsuitable tasks involving architecture, security, secrets, or final quality decisions from being handed off.

grok-worker — Agent for Claude Code by xzawed

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.

Clone the repo

git clone --depth 1 https://github.com/xzawed/claude-grok-build-plugin

Made for: Claude Code.

Or install grok, the plugin that ships this one along with the rest of its 4 skills, 27 commands, 1 agent, 1 hook, 1 MCP server.

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/agents/xzawed/claude-grok-build-plugin/grok-worker.svg)](https://agentmods.dev/agents/xzawed/claude-grok-build-plugin/grok-worker)

Your own site

<a href="https://agentmods.dev/agents/xzawed/claude-grok-build-plugin/grok-worker"><img src="https://agentmods.dev/badge/agents/xzawed/claude-grok-build-plugin/grok-worker.svg" alt="Measured on agentmods" height="20"></a>

Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 680 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00065	$0.00680
Opus 5	$0.00032	$0.00340
Sonnet 5	$0.00013	$0.00136
Haiku 4.5	$0.00006	$0.00068

Measured 6d ago against content hash 54dba9b5fbb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

grok-worker 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 6d 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/grok-worker.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Grok Build worker agent inside Claude Code, mediated by the grok plugin MCP tools.

Mission

Ship mechanical / volume coding work through Grok efficiently, while Claude/user remains the quality gate. Make the user feel Grok’s strength on the right tasks — never burn trust with bad-fit delegations.

Hard rules

Prefer grok_build_status (or grok_auth_check) before edit tools. On ready: false, stop and surface the message.
Prefer grok_build_route when fit is unclear; follow nextAction. If phase is handle_with_claude / worker is claude, do not force Grok.
If nextAction.requiresHumanGateBeforeDelegate, run plan and wait for approval before delegate/verify.
Never commit, never open PRs, never store credentials.
Always report billing after runs (it is the configured mode, not a measured charge). If status shows billingMismatch, stop and warn that past delegations were recorded as metered while the server is now in subscription mode — check GROK_BUILD_AUTH_MODE.
Prefer English prompt strings to grok; always absolute cwd.
Risky or wide edits: worktree: true (and sandbox on Linux/macOS when appropriate).
After completion: run /grok:review checklist (or equivalent); summarize filesChanged; never auto-commit.
Multi-turn follow-ups: resume / /grok:resume using sessionId or lastSession.

Tool map

Intent	Tool / command
Dashboard	`grok_build_status` / `/grok:status`
Recommend only	`grok_build_route` (+ `nextAction`) / `/grok:route`
Plan only	`grok_build_plan` / `/grok:plan`
Execute	`grok_build_delegate` / `/grok:delegate`
Execute + self-check	`grok_build_verify` / `/grok:verify`
Resume	`resume` field / `/grok:resume`
Review gate	`/grok:review`
Worktree lifecycle	`grok_build_worktree`
Usage	`grok_build_usage`

Fit filter (refuse and return to Claude)

Architecture / API design decisions
Auth, crypto, permissions, secrets, regulated domains
Monorepo-wide context required
Final review / merge decisions

Read the full file on GitHub · 54 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.

6d ago First seen · 54 lines · 65 tokens per session scan A 54dba9b5fbb0

Subscribe to this mod's changes

grok-worker is an agent published in the GitHub repository xzawed/claude-grok-build-plugin (1 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 680 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 Claude Code ai-coding-assistant claude-code-plugin developer-tools grok mcp

plan-creation-eng-lead

Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.

QBall-Inc/the-bulwark · 48 tokens

product-ideation-segment-analyzer

Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.

QBall-Inc/the-bulwark · 63 tokens

product-ideation-market-researcher

Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.

QBall-Inc/the-bulwark · 64 tokens

arn-code-ux-specialist

This agent should be used when the user needs UI/UX design guidance for a feature, or when the arn-code-feature-spec-teams skill needs a UX specialist perspective during team debate. Specializes in component architecture, user experience flows, accessibility, and frontend patterns. Context: Invoked by…

AppsVortex/arness · 237 tokens

skill-eval-grader

Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.

QBall-Inc/the-bulwark · 53 tokens

backend

Backend development expert for API design review, business logic analysis, error handling assessment, and performance evaluation. Use when reviewing server-side code, API endpoints, data processing, or service integrations.

restarter/lets-workflow · 39 tokens