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-plangit 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-plan)<a href="https://agentmods.dev/skills/phj128/autoworker/subtask-plan"><img src="https://agentmods.dev/badge/skills/phj128/autoworker/subtask-plan/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-plan"><img src="https://agentmods.dev/badge/skills/phj128/autoworker/subtask-plan.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 | $0.00044 | $0.01180 |
| Opus 5.5 | $0.00018 | $0.00472 |
| Sonnet 5.5 | $0.00009 | $0.00236 |
| Haiku 4.5 | $0.00004 | $0.00118 |
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 2mo 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 — 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).
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.
- 2mo ago First seen · 126 lines · 44 tokens per session scan A 8a055e0a9d10
subtask-plan is a skill published in the GitHub repository phj128/autoworker (18 stars, last pushed 7mo ago), licensed MIT. It adds 44 tokens to every session and 1,180 once invoked, about $0.0002 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-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.
repo-audit
Use this skill when the user wants to audit a repository for baseline compliance, check code quality, security posture, CI/CD setup, testing, documentation, and ecosystem configuration. Runs 9 checklist categories and emits a Markdown report plus JSON sidecar at .orchestrator/metrics/repo-audit- .json. Context: User…
ux-grill
Use when a running web app's UX has to be audited reproducibly rather than by feel — a deterministic mechanical pass over routes and viewports (axe, target size, horizontal overflow, page title, scripted journeys) followed by a screenshot-grounded interrogation of the operator, journey by journey, with two persona…
playwright-driver
Use this skill when executing web tests via the canonical playwright npm package (Microsoft, Apache-2.0). Dispatched by skills/test-runner/ to execute web tests against a target, captures token-frugal AX-tree snapshots + screenshots + console output under .orchestrator/metrics/test-runs/ /, and exits with…
test-runner
Use this skill when orchestrating agentic end-to-end tests. Resolves target + profile, dispatches the right driver(s) (playwright for web today, peekaboo for macOS (issue #381)), invokes the ux-evaluator agent (opus, read-only) against driver artifacts, reconciles findings with the open issue tracker via…