subtask-plan

subtask-plan is a skill for Claude Code, Codex from phj128/autoworker. It costs 44 tokens per session (1,180 once invoked), scanned A, original, MIT.

A skill that completes a subtask's verification plan after its initial document exists. It adds links to the approved plan, four levels of tests, and a final self-check.

In plain words
What is it for?
Use it after subtask-init to fill the traceability table, define L1 through L4 checks, and confirm that the active subtask has the required information.
Why use it?
It makes the subtask ready for implementation by connecting planned work to verification steps and checking that the initial documentation is complete.

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-plan
Any agent
npx skills add phj128/autoworker --skill subtask-plan
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-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/phj128/autoworker/subtask-plan.svg)](https://agentmods.dev/skills/phj128/autoworker/subtask-plan)
Your own site
<a href="https://agentmods.dev/skills/phj128/autoworker/subtask-plan"><img src="https://agentmods.dev/badge/skills/phj128/autoworker/subtask-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,180 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 5.1 $0.00044 $0.01180
Opus 5 $0.00022 $0.00590
Sonnet 5 $0.00009 $0.00236
Haiku 4.5 $0.00004 $0.00118

Measured 5d ago against content hash 8a055e0a9d10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

subtask-plan 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 5d 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-plan/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

autoworker:subtask-plan — Complete Verification Plan (Gate 1.3 Step C+D+E)

Invoked after autoworker:subtask-init completes. Fills in upstream traceability table, L1-L4 verification plan, and solution self-check.

Execution Flow

1. Locate and Check Subtask

Glob `subtask_*.md` (exclude subtask_template.md) →
  0 found → stop, prompt to create subtask
  1 found → use directly (backward compatible)
  multiple → grep `status:` to filter:
    - Files without status field treated as active (backward compatible)
    - Exactly 1 active → use it
    - 0 active → list all files + status, prompt user to choose
    - >1 active → report anomaly
→ Read → check first-half completeness

Pre-checks:

  • Assumptions table "Result" column has empty rows → FAIL, prompt to complete autoworker:subtask-init first
  • User confirmation record is empty → FAIL
  • Goal/success criteria is empty → FAIL

2. Fill In Upstream Verification Traceability Table

Source: Read plan file (if exists) + review conversation for user's verification/testing requirements.

Edit subtask's "Upstream Verification Traceability" table:

Upstream text (copy verbatim) Subtask item Delta rationale

Rules:

  • Copy verbatim from upstream text — not summarize (the act of copying forces you to see what upstream required)
  • When no upstream requirements exist, write one line: No upstream requirements | Self-designed | —
  • Subsequent L1-L4 are not allowed to be lower than the traceability table; downgrades must state delta rationale

2.5. Silent Failure Analysis

Read the subtask's "Acceptance Criteria" table, for each metric ask:

If this metric deviates, which L1-L4 layer would catch it?

  • Metric has no corresponding test → add in subsequent L2-L4
  • All metrics have corresponding tests → continue

Purpose: Prevent acceptance criteria defined in the plan but not covered by the verification plan (silent failure).

Read the full file on GitHub · 126 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. 5d ago First seen · 126 lines · 44 tokens per session scan A 8a055e0a9d10

Subscribe to this mod's changes

subtask-plan is a skill published in the GitHub repository phj128/autoworker (17 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 1,180 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.