A command that sends the user's request to a separate Grok Build agent for investigation, fixes, or follow-up work. It also supports handing off longer-running work.

Delegating investigations, explicit code fixes, and follow-up tasks to the Grok Build subagent.

It lets another agent take ownership of a delegated task while preserving the stated request and its execution rules.

delegate — Command for coding agents by kai-wedekind: A command that sends the user's request to a…

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 commands/kai-wedekind/claude-code-grok-bridge/delegate

Clone the repo

git clone --depth 1 https://github.com/kai-wedekind/claude-code-grok-bridge

Or install grok-build, the plugin that ships this one along with the rest of its 3 skills, 7 commands, 1 agent, 2 hooks.

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/commands/kai-wedekind/claude-code-grok-bridge/delegate.svg)](https://agentmods.dev/commands/kai-wedekind/claude-code-grok-bridge/delegate)

Your own site

<a href="https://agentmods.dev/commands/kai-wedekind/claude-code-grok-bridge/delegate"><img src="https://agentmods.dev/badge/commands/kai-wedekind/claude-code-grok-bridge/delegate.svg" alt="Measured on agentmods" height="20"></a>

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,309 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 86% copy Near-identical to another mod 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	$0.00020	$0.01309
Opus 5	$0.00010	$0.00655
Sonnet 5	$0.00004	$0.00262
Haiku 4.5	$0.00002	$0.00131

Measured 4d ago against content hash 439910d2d3ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

delegate 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 4d 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.

Origin

This is a copy

86% identical to delegate — 28 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/grok-build/commands/delegate.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Invoke the grok-build:grok-delegate subagent via the Agent tool (subagent_type: "grok-build:grok-delegate"), forwarding the raw user request as the prompt. grok-build:grok-delegate is a subagent, not a skill — do not call Skill(grok-build:grok-delegate) (no such skill) or Skill(grok-build:delegate) (that re-enters this command and hangs the session). The command runs inline so the Agent tool stays in scope; forked general-purpose subagents do not expose it. The final user-visible response must be Grok's output verbatim.

Raw user request: $ARGUMENTS

Background ownership model (one policy for command, agent, and skill):

Bridge --background owns the long-running process group (detached run-worker + grok agent). That is what records bridgePid and agentPid so /grok-build:stop can kill both trees.
Claude Code background (Agent run_in_background / short Bash enqueue) is only for the enqueue hop, never for holding the long Grok process.
Prefer bridge --background for long or open-ended work. Ensure the forwarded run call includes --background when background mode is chosen (add it if missing).
If the request includes --wait, run the subagent in the foreground and do not pass --background to run.
If neither flag is present, default to foreground for a small, clearly bounded request; for complicated or long work, prefer background and pass bridge --background.
--wait is Claude-side only (foreground vs enqueue). Do not treat it as task text. --background is a bridge flag when long work is chosen — forward it to run, and do not leave it in the natural-language task text.
--model, --effort, --write, --thread, --json-schema, --cwd, --prompt-file, --prompts-file, --timeout-ms, and --max-turns are runtime controls. Preserve them for the forwarded run call; do not treat them as task text.
Mutual exclusions the bridge enforces: --resume/--resume-last vs --fresh; --thread vs --resume-last. If both --background and --wait appear, treat as wait/foreground.
--prompts-file is a sequential NDJSON batch on the bridge run path; it cannot be combined with --background, --prompt-file, or a positional prompt.

Execution mode:

If the request includes --background, run the grok-build:grok-delegate subagent for a short enqueue only, with bridge --background on the run call.
If the request includes --wait, run the grok-build:grok-delegate subagent in the foreground.
If the request includes --resume, do not ask whether to continue. The user already chose.
If the request includes --fresh, do not ask whether to continue. The user already chose.
Otherwise, before starting Grok, check for a resumable delegate thread from this Claude session by running:

node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-bridge.mjs" run-resume-candidate --json

If that helper reports available: true, use AskUserQuestion exactly once to ask whether to continue the current Grok thread or start a new one.
The two choices must be:
- Continue current Grok thread
- Start a new Grok thread
If the user is clearly giving a follow-up instruction such as "continue", "keep going", "resume", "apply the top fix", or "dig deeper", put Continue current Grok thread (Recommended) first.
Otherwise put Start a new Grok thread (Recommended) first.
If the user chooses continue, add --resume before routing to the subagent.
If the user chooses a new thread, add --fresh before routing to the subagent.
If the helper reports available: false, do not ask. Route normally.

Operating rules:

The subagent is a thin forwarder only. It should use one Bash call to invoke node "${CLAUDE_PLUGIN_ROOT}/scripts/grok-bridge.mjs" run ... and return that command's stdout as-is.
Return the Grok bridge stdout verbatim to the user.
Do not paraphrase, summarize, rewrite, or add commentary before or after it.
Do not ask the subagent to inspect files, monitor progress, poll /grok-build:runs, fetch /grok-build:show, call /grok-build:stop, summarize output, or do follow-up work of its own.
Leave --effort unset unless the user explicitly asks for a specific reasoning effort.
Leave the model unset unless the user explicitly asks for one.
Leave --resume and --fresh in the forwarded request. The subagent handles that routing when it builds the run command.
Default write policy is read-only; --write only for explicit create/edit/fix requests.
If the helper reports that Grok is missing or unauthenticated, stop and tell the user to run /grok-build:check.
If the user did not supply a request, ask what Grok should investigate or fix.

Read the full file on GitHub · 57 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.

4d ago First seen · 57 lines · 20 tokens per session scan A 439910d2d3ba

Subscribe to this mod's changes

delegate is a command published in the GitHub repository kai-wedekind/claude-code-grok-bridge (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,309 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to delegate, differing in 28 lines, and is treated as a copy.

Building agents ai-agents apache-2-0 claude-code developer-tools grok plugin

delegate

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

How it starts

What this file has done since we first saw it

Other commands, from other repositories

delegate

review

login

review

adversarial-review

rescue