ultrawork-exec

ultrawork-exec is a command for Claude Code from mnthe/hardworker-marketplace. It costs 16 tokens per session (3,410 once invoked), scanned A, original, MIT.

A command that runs an ultrawork plan through its task waves, checks the results, and retries failed tasks. It uses separate agents for execution, verification, and documentation.

In plain words
What is it for?
Use it to execute an existing ultrawork plan, delegate coding and checks to agents, and continue until the plan passes or reaches its retry limit.
Why use it?
It coordinates repeated task attempts and verification without requiring the whole workflow to be managed manually.

Command for Claude Code

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

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 execute an existing ultrawork plan, delegate coding and checks to agents, and continue until the plan passes or reaches its retry limit.

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-exec

README.md
[![agentmods](https://agentmods.dev/badge/commands/mnthe/hardworker-marketplace/ultrawork-exec.svg)](https://agentmods.dev/commands/mnthe/hardworker-marketplace/ultrawork-exec)
Your own site
<a href="https://agentmods.dev/commands/mnthe/hardworker-marketplace/ultrawork-exec"><img src="https://agentmods.dev/badge/commands/mnthe/hardworker-marketplace/ultrawork-exec.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,410 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 $0.00016 $0.03410
Opus 5 $0.00008 $0.01705
Sonnet 5 $0.00003 $0.00682
Haiku 4.5 $0.00002 $0.00341

Measured 7d ago against content hash e6d1b04e9674, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ultrawork-exec 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 7d 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-exec.md · 447 lines

How it starts

The opening of the file, as written. The whole thing — 447 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ultrawork Exec Command

Execute a plan created by /ultrawork-plan. Includes automatic retry loop for failed tasks and verification.


Overview

/ultrawork-exec
    ↓
Load Session → Execute Tasks (waves) → Verify → Retry if failed
    ↓
Loop until: PASS or max_iterations reached

Delegation Rules (MANDATORY)

The orchestrator MUST delegate work to sub-agents. Direct execution is prohibited.

Phase Delegation Direct Execution
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

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


Sub-agent Execution

Sub-agents can be run in foreground (default) or background mode. Choose based on the situation:

Mode When to Use
Foreground Sequential tasks, need result immediately
Background Parallel execution with worker pool limits

Parallel execution: Call multiple Tasks in a single message for automatic parallelization.


Session ID Handling

All scripts require --session <id> flag.

Claude Code v2.1.9+ automatically replaces ${CLAUDE_SESSION_ID} with the actual session UUID.

# Use ${CLAUDE_SESSION_ID} directly - it gets auto-replaced
bun "${CLAUDE_PLUGIN_ROOT}/src/scripts/session-get.js" --session ${CLAUDE_SESSION_ID} --field phase
bun "${CLAUDE_PLUGIN_ROOT}/src/scripts/session-update.js" --session ${CLAUDE_SESSION_ID} --phase EXECUTION
bun "${CLAUDE_PLUGIN_ROOT}/src/scripts/task-list.js" --session ${CLAUDE_SESSION_ID} --format json

Read the full file on GitHub · 447 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. 7d ago First seen · 447 lines · 16 tokens per session scan A e6d1b04e9674

Subscribe to this mod's changes

ultrawork-exec is a command published in the GitHub repository mnthe/hardworker-marketplace (4 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 3,410 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.