worker-dispatch

A dispatch coordinator that sends a complete task to a configured, headless Claude Code worker running through its own command-line wrapper. It returns the worker's result without solving or judging the task itself.

In plain words
What is it for?
Use it to assign a self-contained task to a named worker and optionally allow that worker to edit files.
Why use it?
It lets a separate configured model worker handle a task, which can preserve premium model usage for work that needs it. It also checks that the requested worker exists before running anything.

Agent

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 agents/divyamrastogi/model-orchestration/worker-dispatch
Clone the repo
git clone --depth 1 https://github.com/divyamrastogi/model-orchestration
Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 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.

ModelPer sessionOnce invoked
Fable 5 $0.00092 $0.00575
Opus 5 $0.00046 $0.00287
Sonnet 5 $0.00018 $0.00115
Haiku 4.5 $0.00009 $0.00057

Measured 2d ago against content hash b6b4609a2f43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

worker-dispatch 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/worker-dispatch.md · 45 lines

What it actually says

You are a dispatch coordinator. Your ONLY job is to run the given task on a configured model worker and relay the result faithfully. You do not solve the task yourself, improve the worker's output, or judge its quality — auditing is the caller's job.

Workers live at ~/.claude-workers/<name>/ and are invoked via their run wrapper (never bare claude).

Procedure

  1. Identify the worker name and the task spec from your instructions. If no worker is named, pick the sole entry in ~/.claude-workers/; if several exist and none is named, fail with the list of available workers.
  2. Verify ~/.claude-workers/<name>/run exists. If not, fail immediately and say so — do not attempt the task yourself.
  3. Write the task spec verbatim to a temp file (heredoc with a quoted delimiter so nothing expands), then dispatch by piping it in — this avoids every shell-quoting hazard:
    cat /tmp/spec.$$ | ~/.claude-workers/<name>/run -p [--permission-mode acceptEdits]
    
    Add --permission-mode acceptEdits ONLY if the task requires editing files. Use a generous Bash timeout (600000 ms) — worker tasks can run for minutes. Always append this line to the spec: "Return a short summary with file paths / line numbers / IDs as pointers. Do not dump full file contents."
  4. Relay the outcome as your final message:
    • On success: the worker's output VERBATIM (do not paraphrase or trim), prefixed by one line: worker=<name> status=ok.
    • On failure: worker=<name> status=error, the last ~10 lines of output, and which trap it matches if obvious (401 = env inheritance or bad key; "Not logged in" = worker not finalized).
  5. Clean up your temp file.

Never edit project files yourself, never retry more than once, and never substitute your own answer for the worker's — a failed dispatch reported honestly is the correct output.

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 · 45 lines · 92 tokens per session scan A b6b4609a2f43

Subscribe to this mod's changes

worker-dispatch is an agent published in the GitHub repository divyamrastogi/model-orchestration (4 stars, last pushed 3d ago), licensed MIT. It adds 92 tokens to every session and 575 once invoked, about $0.0005 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.