subtask-update

subtask-update is a skill for Claude Code, Codex from phj128/autoworker. It costs 77 tokens per session (1,111 once invoked), scanned A, original, MIT.

A workflow for updating a coding subtask after a failed check or a problem found during testing. It adds corrective steps and sends the work back through the project’s automated task loop.

In plain words
What is it for?
Use it after a gate check fails or when testing reveals bugs, missing tests, unverified links, or uncovered files.
Why use it?
It turns test findings into specific fixes and verification steps instead of leaving the task plan out of date.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/phj128/autoworker/subtask-update.svg)](https://agentmods.dev/skills/phj128/autoworker/subtask-update)
Your own site
<a href="https://agentmods.dev/skills/phj128/autoworker/subtask-update"><img src="https://agentmods.dev/badge/skills/phj128/autoworker/subtask-update.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,111 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 $0.00077 $0.01111
Opus 5 $0.00039 $0.00556
Sonnet 5 $0.00015 $0.00222
Haiku 4.5 $0.00008 $0.00111

Measured 4d ago against content hash 438b4cf1b762, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

subtask-update 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-update/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

autoworker:subtask-update — Supplement/Correct Subtask Plan

Two trigger modes:

  • Mode A: Automatically called after autoworker:gate-check FAIL (no arguments)
  • Mode B: User calls manually with a finding/bug description

Both modes ultimately return to the autoworker:dispatch loop.

Mode Determination

Has user-provided argument?
  ├─ Yes → Mode B (user feedback)
  └─ No  → Mode A (gate-check FAIL)

Mode A: Auto-Called After gate-check FAIL

A1. Read gate-check FAIL Information

Extract from conversation context the autoworker:gate-check FAIL output:

  • Which self-check items didn't pass
  • Which change points have confidence < 95%
  • What's specifically missing (untested tests, unverified links, uncovered files, etc.)

A2. Design Supplementary Steps

For each failed item, design specific supplementary steps:

  • What code/scripts to write (e.g., test scripts, verification scripts)
  • What operations to execute (e.g., restart service, run end-to-end test)
  • What the expected result is

A3. Update subtask → jump to "Common Steps: Update subtask + Chain"


Mode B: User Feedback Trigger

B1. Understand User Feedback

Extract the problem found by user from the argument. Examples:

  • "Tags have no spaces between them" → tag input has a bug in the publish feature
  • "deleteNote click does nothing" → DOM selector may have broken
  • "Received note list format is wrong" → tool return format issue

B2. Read Current Subtask + Locate Context

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 → extract:
- Current Phase/Step progress
- Which tests have passed
- Related reference file list

Read the full file on GitHub · 136 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 · 136 lines · 77 tokens per session scan A 438b4cf1b762

Subscribe to this mod's changes

subtask-update is a skill published in the GitHub repository phj128/autoworker (17 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 1,111 once invoked, about $0.0004 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

flow-next-pilot

Single-tick autonomous build-loop conductor. One spec or the backlog, one stage per tick (pipeline.chainStages chains qa into make-pr), emits PILOTVERDICT. Use when asked to pilot a spec or backlog.

gmickel/flow-next · 49 tokens

backlog

Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…

umputun/cc-thingz · 96 tokens

to-roadmap

Capture a multi-task initiative into .task/roadmap/ .md — a phase-grouped backlog of ready-to-pick-up items.

SpaiR/task-pipeline · 34 tokens

flow

Orchestrator for Ticket-Flow — default is --local (all phases in this session with user checkpoints). --parallel works multiple ready tickets at once via worktree-isolated subagents in this session; --serial (one subagent at a time, merge+deploy+cleanup per ticket) and --loop (re-query the ready queue after every…

keefar/ticket-flow · 292 tokens

setup-working-genius

Per-repo configuration — pin the work-file directory, verify commands, and issue tracking, seed the project docs, and leave the pointer that tells every future session this project works this way.

donald-ada/workinggenius · 43 tokens

init

Scaffold a ticket-flow project — one-time setup; trigger on "setz ticket-flow auf", "richte das Projekt für ticket-flow ein", "set up ticket-flow here". Runs bd init with tf's agents template (keeps Claude Code's own memory system), scaffolds spec dirs and worktree settings, migrates an existing KANBAN.md into beads.…

keefar/ticket-flow · 108 tokens