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.
/plugin marketplace add mnthe/hardworker-marketplace/plugin install ultraworkWrote 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.
[](https://agentmods.dev/commands/mnthe/hardworker-marketplace/ultrawork)<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.
<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>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 | $0.00014 | $0.06283 |
| Opus 5 | $0.00007 | $0.03141 |
| Sonnet 5 | $0.00003 | $0.01257 |
| Haiku 4.5 | $0.00001 | $0.00628 |
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.
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").
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.
- 8d ago First seen · 754 lines · 14 tokens per session scan A bdcaa3b9d5cb
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.