task-tool

task-tool is a skill for Claude Code, Codex from heyhuynhgiabuu/openpi. It costs 56 tokens per session (531 once invoked), scanned A, original, MIT.

A guide for using a task tool to assign work to specialist subagents, such as scouts, planners, reviewers, or workers.

In plain words
What is it for?
Delegating new work, resuming a previously successful background task, or continuing a durable specialist conversation when explicitly needed.
Why use it?
It prevents invalid task calls, such as adding IDs to new tasks or inventing identifiers, which can make delegation fail.

Skill for Claude CodeCodex

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 skills/heyhuynhgiabuu/openpi/task-tool
Any agent
npx skills add heyhuynhgiabuu/openpi --skill task-tool
Clone the repo
git clone --depth 1 https://github.com/heyhuynhgiabuu/openpi

Made for: Claude Code, Codex.

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-tool

README.md
[![agentmods](https://agentmods.dev/badge/skills/heyhuynhgiabuu/openpi/task-tool.svg)](https://agentmods.dev/skills/heyhuynhgiabuu/openpi/task-tool)
Your own site
<a href="https://agentmods.dev/skills/heyhuynhgiabuu/openpi/task-tool"><img src="https://agentmods.dev/badge/skills/heyhuynhgiabuu/openpi/task-tool.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 531 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 $0.00056 $0.00531
Opus 5 $0.00028 $0.00266
Sonnet 5 $0.00011 $0.00106
Haiku 4.5 $0.00006 $0.00053

Measured 4d ago against content hash 692e8a2574a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-tool 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 4d 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.

.pi/skills/task-tool/SKILL.md · 50 lines

What it actually says

Rules (matches pi-task v0.2.0)

  1. Never pass task_id on a fresh delegation. Omit the field. task_id is for resuming an existing background task only.
  2. Never pass conversation_id unless the user explicitly asked for a durable specialist conversation.
  3. Never invent UUIDs as task_id or agent_id. The tool will reject them.
  4. Only use a task_id that came back in a successful prior task result. Never reuse one from an error message or old history.
  5. If a task call returns Unknown task_id: "...", re-issue without task_id and without conversation_id.

Call shapes

Fresh:

{ "agent_type": "scout", "description": "Research X", "prompt": "..." }

Background (default in pi-task):

{ "agent_type": "scout", "description": "Research X", "background": true, "prompt": "..." }

Resume (only with a valid task_id from a prior result):

{ "agent_type": "scout", "task_id": "m1lxyz-a1b2", "description": "Continue", "prompt": "..." }

Durable conversation (only when the user asked for one):

{ "agent_type": "scout", "conversation_id": "research-ai", "description": "Continue", "prompt": "..." }

Anti-patterns

  • task_id on a fresh call.
  • task_id as a UUID.
  • conversation_id without the user asking.
  • Resuming a task that was never successfully started.

Error recovery

Error Fix
Unknown task_id: "..." Re-issue without task_id (fresh task) or use a conversation_id
Unknown agent: "..." Use one of: scout, explore, planner, reviewer, vision, worker
task_id/conversation_id mismatch Use the task_id that maps to your conversation_id
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. 4d ago First seen · 50 lines · 56 tokens per session scan A 692e8a2574a7

Subscribe to this mod's changes

task-tool is a skill published in the GitHub repository heyhuynhgiabuu/openpi (212 stars, last pushed 22d ago), licensed MIT. It adds 56 tokens to every session and 531 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens