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.
npx skills add phj128/autoworker --skill subtask-updategit clone --depth 1 https://github.com/phj128/autoworkerWrote 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.
[](https://agentmods.dev/skills/phj128/autoworker/subtask-update)<a href="https://agentmods.dev/skills/phj128/autoworker/subtask-update"><img src="https://agentmods.dev/badge/skills/phj128/autoworker/subtask-update/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/phj128/autoworker/subtask-update"><img src="https://agentmods.dev/badge/skills/phj128/autoworker/subtask-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.01111 |
| Opus 5.5 | $0.00031 | $0.00444 |
| Sonnet 5.5 | $0.00015 | $0.00222 |
| Haiku 4.5 | $0.00008 | $0.00111 |
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 1mo 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.
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-checkFAIL (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
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.
- 1mo ago First seen · 136 lines · 77 tokens per session scan A 438b4cf1b762
subtask-update is a skill published in the GitHub repository phj128/autoworker (18 stars, last pushed 6mo ago), licensed MIT. It adds 77 tokens to every session and 1,111 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
flow-next-features
Seed or maintain the committed user-POV drive map at .flow/features/ so QA and drive reuse how a user reaches each feature.
flow-next-flow
Use first in a Flow-Next repo for a spec id, change, bug, issue, slow code or metric, cleanup, design fork, dump to explain, repeated mistake, prompt change, what could break, what next. No quick asks.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
flow-next-plan
Plan a feature into a flow-next spec with tasks in .flow/. Use when asked to plan, spec out, or break down work (fn-N ids).
flow-next
Manage .flow/ tasks and specs. Use for show or list tasks, task status, what is ready, show fn-N. NOT for planning or executing (use the plan and work skills).
flow-next-qa
Live-app QA pass derived from the spec. Drives the running app, files P0/P1/P2 findings with evidence, emits a YES or NO qaverdict receipt.