subtask-init

subtask-init is a skill for Claude Code, Codex from phj128/autoworker. It costs 49 tokens per session (1,167 once invoked), scanned A, original, MIT.

A skill that creates the first half of a subtask document after the user confirms the work plan. It records the goal, success criteria, user decisions, assumptions, and results of automatic checks.

In plain words
What is it for?
Use it after plan confirmation to create or update a numbered subtask file, capture measurable acceptance criteria, and document verified or unresolved assumptions.
Why use it?
It turns an agreed plan into a documented starting point before code is written, while checking assumptions that depend on outside systems.

Skill for Claude CodeCodex

Part of the autoworker plugin — 11 skills, 1 command shipped together

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/phj128/autoworker/subtask-init
Any agent
npx skills add phj128/autoworker --skill subtask-init
Clone the repo
git clone --depth 1 https://github.com/phj128/autoworker

Made for: Claude Code, Codex.

Or install autoworker, the plugin that ships this one along with the rest of its 11 skills, 1 command.

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 subtask-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/phj128/autoworker/subtask-init.svg)](https://agentmods.dev/skills/phj128/autoworker/subtask-init)
Your own site
<a href="https://agentmods.dev/skills/phj128/autoworker/subtask-init"><img src="https://agentmods.dev/badge/skills/phj128/autoworker/subtask-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,167 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 $0.00049 $0.01167
Opus 5 $0.00024 $0.00583
Sonnet 5 $0.00010 $0.00233
Haiku 4.5 $0.00005 $0.00117

Measured 4d ago against content hash ff4ff170df5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

subtask-init 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.

skills/subtask-init/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

autoworker:subtask-init — Create Subtask First Half (Gate 1.3 Step A+B)

After Plan Mode discussion is complete and user has confirmed direction, invoke this skill to create the first half of subtask.md.

Execution Flow

1. Determine Sequence Number

Glob `subtask_*.md` (current directory) + Glob `claude_docs/subtask/*.md` (archive)
→ Extract all sequence numbers → take max + 1

2. Extract Confirmation Record from Conversation Context

Review the conversation and extract:

  • Confirmation method: AskUserQuestion / confirmed in plan discussion / explicit in user instruction
  • Key Q&A: scope, completion criteria, constraints, preferences
  • Goal: WHY + WHAT (1-3 sentences)
  • Success criteria: specific measurable items
  • Acceptance criteria: Extract quantifiable metrics from plan (metric name + measurement method + expected value/range + tolerance). When no quantitative metrics exist, explicitly write "No quantitative metrics, reason: "

3. Identify Core Assumptions

Extract assumptions that depend on external systems from plan and conversation. Each assumption needs:

  • Assumption description (I assume X because Y)
  • Verification experiment (one-line command)

Pure internal logic changes (e.g., refactoring, documentation): Write one line No external dependencies | — | —.

4. Search for Reference Files

Glob/Grep search for related files → confirm paths and line numbers

Do not guess line numbers — must Read to confirm.

5. Extract Design Decisions and Plan

Extract from plan file / conversation:

  • Design decisions (decision point + choice + reason)
  • Implementation plan (Phase/Step structure)

5.5. Pause Old Active Subtask

Glob `subtask_*.md` (exclude subtask_template.md) →
  For each file grep `status: active` →
    Edit all found to `status: paused`

Purpose: Ensure at most 1 active subtask at any time. Creating a new subtask automatically pauses old ones.

6. Write Subtask First Half

Read the full file on GitHub · 123 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. 4d ago First seen · 123 lines · 49 tokens per session scan A ff4ff170df5b

Subscribe to this mod's changes

subtask-init is a skill published in the GitHub repository phj128/autoworker (17 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 1,167 once invoked, about $0.0002 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.