subtask

A command-line tool for assigning work to multiple AI workers, with each worker operating in a separate Git worktree, which is an isolated copy of a code repository.

In plain words
What is it for?
Use it to split research, planning and implementation into tasks, track worker progress, review results, request changes and merge completed work after approval.
Why use it?
It removes the need to perform every investigation or coding task yourself and helps prevent parallel workers from editing the same files.

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/zippoxer/subtask/install
Any agent
npx skills add zippoxer/subtask --skill install
Clone the repo
git clone --depth 1 https://github.com/zippoxer/subtask

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,157 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 $0.00057 $0.01157
Opus 5 $0.00028 $0.00579
Sonnet 5 $0.00011 $0.00231
Haiku 4.5 $0.00006 $0.00116

Measured 2d ago against content hash 476140dd6e44, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

subtask 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 2d 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.

pkg/install/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subtask

Subtask is a CLI for orchestrating parallel AI workers. There are three roles: the user who gives direction, you (the lead) who orchestrates and delegates, and workers who execute tasks.

Each worker runs in an isolated git worktree. They can't conflict with each other.

The user tells you what they need. You clarify requirements, break work into tasks, dispatch to workers, review their output, iterate until it's right, and merge when ready.

Prefer to delegate exploration, research and planning to workers as parts of their tasks. Workers have time & space to dig deep, whereas you should preserve context to lead. Only go into details yourself when user explicitly requested, or the situation calls for it.

Mindset

  1. Understand before delegating — ask questions, clarify requirements. Don't rush to create tasks until you understand what the user actually wants.
  2. Own the complexity — stay on top of all tasks. Surface progress and blockers. Don't make the user chase status.
  3. Work autonomously — review output, request changes, iterate with workers. Only involve the user for decisions they need to make.
  4. Ask before merging — get user sign-off before merging. Don't merge without user approval.

Commands

Command Description
subtask ask "..." Quick question (no task, runs in cwd)
subtask draft <task> --base-branch <branch> --title "..." <<'EOF' Create a task
subtask send <task> <prompt> Prompt worker on task (blocks until reply)
subtask stage <task> <stage> Advance workflow stage
subtask list View all tasks
subtask show <task> View task details
subtask diff [--stat] <task> Show changes (from merge base)
subtask merge <task> -m "msg" Squash-merge task into base branch
subtask close <task> Close without merging, free workspace
subtask workspace <task> Get workspace path (a git worktree)
subtask interrupt <task> Gracefully stop a running worker
subtask log <task> Show task conversation and history
subtask trace <task> Debug what a worker is doing and thinking internally

Read the full file on GitHub · 107 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 107 lines · 57 tokens per session scan A 476140dd6e44

Subscribe to this mod's changes

subtask is a skill published in the GitHub repository zippoxer/subtask (340 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 1,157 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

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens

map-wayfind

Decision-frontier wayfinding: build and work a durable map of open design decisions BEFORE planning, for large or foggy efforts where /map-plan would force premature decomposition. Use when a task is too big or too vague to decompose — many unknowns, tangled decisions, or "I'm not even sure what to build yet" — and…

azalio/map-framework · 182 tokens

map-fast

Minimal workflow for small, low-risk changes — no planning, no learning.

azalio/map-framework · 17 tokens

clipboard

Copy text to clipboard with optional rich formatting. Triggers on "copy to clipboard", "copy that", "pbcopy", "copy formatted", "copy rich text".

CodeAlive-AI/ai-driven-development · 36 tokens

neo4j-modeling-skill

Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…

neo4j-contrib/neo4j-skills · 152 tokens

alphafold-database

Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.

agent-skills-hub/agent-skills-hub · 54 tokens