ultrawork

ultrawork is a command for Claude Code from mnthe/hardworker-marketplace. It costs 14 tokens per session (6,283 once invoked), scanned A, original, MIT.

A command that starts an Ultrawork session with strict verification. Ultrawork is a workflow that explores a project, plans work, delegates tasks to specialized sub-agents, verifies the results, and documents the outcome.

In plain words
What is it for?
Use it to run interactive or automatic planning, delegate exploration and implementation, verify changes, and produce documentation. It supports planning, execution, verification, and cleanup through the session workflow.
Why use it?
It enforces a repeatable process and requires work to be delegated and checked. This makes progress, evidence, and task ownership visible throughout a larger change.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ultrawork plugin — 15 skills, 9 commands shipped together

Good fit Use it to run interactive or automatic planning, delegate exploration and implementation, verify changes, and produce documentation. It supports planning, execution, verification, and cleanup through the session workflow.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add mnthe/hardworker-marketplace
Claude Code
/plugin install ultrawork

Made for: Claude Code.

Or install ultrawork, the plugin that ships this one along with the rest of its 15 skills, 9 commands.

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 ultrawork

README.md
[![agentmods](https://agentmods.dev/badge/commands/mnthe/hardworker-marketplace/ultrawork/github.svg)](https://agentmods.dev/commands/mnthe/hardworker-marketplace/ultrawork)
Your own site
<a href="https://agentmods.dev/commands/mnthe/hardworker-marketplace/ultrawork"><img src="https://agentmods.dev/badge/commands/mnthe/hardworker-marketplace/ultrawork/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ultrawork

Your own site · 80×15
<a href="https://agentmods.dev/commands/mnthe/hardworker-marketplace/ultrawork"><img src="https://agentmods.dev/badge/commands/mnthe/hardworker-marketplace/ultrawork.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,283 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.06283
Opus 5 $0.00007 $0.03141
Sonnet 5 $0.00003 $0.01257
Haiku 4.5 $0.00001 $0.00628

Measured 8d ago against content hash bdcaa3b9d5cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ultrawork 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 8d 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.

plugins/ultrawork/commands/ultrawork.md · 754 lines

How it starts

The opening of the file, as written. The whole thing — 754 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ultrawork Command

Overview

Ultrawork uses session directory for all task management.

Two Modes:

  • Interactive (default): Orchestrator runs planning skill directly, uses AskUserQuestion
  • Auto (--auto): Planner sub-agent handles planning automatically

Delegation Rules (MANDATORY)

The orchestrator MUST delegate work to sub-agents. Direct execution is prohibited except where explicitly noted.

Phase Delegation Direct Execution
Overview Exploration N/A ALWAYS via Skill(skill="ultrawork:overview-exploration")
Targeted Exploration ALWAYS via Task(subagent_type="ultrawork:explorer") NEVER
Planning (non-auto) N/A ALWAYS (by design)
Planning (auto) ALWAYS via Task(subagent_type="ultrawork:planner") NEVER
Execution ALWAYS via Task(subagent_type="ultrawork:worker") NEVER
Verification ALWAYS via Task(subagent_type="ultrawork:verifier") NEVER
Documentation ALWAYS via Task(subagent_type="ultrawork:documenter") NEVER

Why: Sub-agents are optimized for their specific tasks with proper tool access and context. Direct execution bypasses these optimizations and may produce incomplete results.

Exception: User explicitly requests direct execution (e.g., "run this directly", "execute without agent").

Read the full file on GitHub · 754 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.

  1. 8d ago First seen · 754 lines · 14 tokens per session scan A bdcaa3b9d5cb

Subscribe to this mod's changes

ultrawork is a command published in the GitHub repository mnthe/hardworker-marketplace (4 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 6,283 once invoked, about $0.0001 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.