task-delegator

task-delegator is an agent for coding agents from GabrielBertoli/openclaw-mcp. It costs 26 tokens per session (239 once invoked), scanned A, a copy of task-delegator, MIT.

An agent that sends long-running tasks to OpenClaw, runs them in the background, checks their progress, and reports the result.

In plain words
What is it for?
Use it to queue, monitor, list, or cancel asynchronous OpenClaw tasks.
Why use it?
It avoids making the main conversation wait while a task takes more than a short time to finish.

Agent

Part of the openclaw plugin — 1 skill, 2 commands, 1 agent, 1 MCP server shipped together

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/gabrielbertoli/openclaw-mcp/task-delegator
Clone the repo
git clone --depth 1 https://github.com/GabrielBertoli/openclaw-mcp

Or install openclaw, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 1 agent, 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.

agentmods badge for task-delegator

README.md
[![agentmods](https://agentmods.dev/badge/agents/gabrielbertoli/openclaw-mcp/task-delegator.svg)](https://agentmods.dev/agents/gabrielbertoli/openclaw-mcp/task-delegator)
Your own site
<a href="https://agentmods.dev/agents/gabrielbertoli/openclaw-mcp/task-delegator"><img src="https://agentmods.dev/badge/agents/gabrielbertoli/openclaw-mcp/task-delegator.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 239 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% 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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00239
Opus 5 $0.00013 $0.00120
Sonnet 5 $0.00005 $0.00048
Haiku 4.5 $0.00003 $0.00024

Measured 3d ago against content hash 99b2d991fd43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-delegator 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.

Origin

This is a copy

100% identical to task-delegator — 0 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/claude/openclaw/agents/task-delegator.md · 34 lines

What it actually says

You are a task delegation agent that sends work to OpenClaw and monitors completion.

Your Task

When given a task to delegate, send it to OpenClaw asynchronously and monitor until complete.

Process

  1. Send task: Use openclaw_chat_async to queue the task
  2. Monitor: Poll openclaw_task_status periodically
  3. Report: Return the result when complete

Available Tools

Tool Purpose
openclaw_chat_async Queue a message, get task_id
openclaw_task_status Check task progress
openclaw_task_list List all tasks
openclaw_task_cancel Cancel pending task

Guidelines

  • Use async for tasks that might take > 30 seconds
  • Poll status every 5-10 seconds
  • Report partial progress if available
  • Cancel stuck tasks after reasonable timeout
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. 3d ago First seen · 34 lines · 26 tokens per session scan A 99b2d991fd43

Subscribe to this mod's changes

task-delegator is an agent published in the GitHub repository GabrielBertoli/openclaw-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 26 tokens to every session and 239 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to task-delegator, differing in 0 lines, and is treated as a copy.