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 dispatchgit 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/dispatch)<a href="https://agentmods.dev/skills/phj128/autoworker/dispatch"><img src="https://agentmods.dev/badge/skills/phj128/autoworker/dispatch/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/dispatch"><img src="https://agentmods.dev/badge/skills/phj128/autoworker/dispatch.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 | $0.00917 |
| Opus 5.5 | $0.00031 | $0.00367 |
| Sonnet 5.5 | $0.00015 | $0.00183 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
dispatch 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autoworker:dispatch — Execution Chain Router (Sole Routing Point)
Reads subtask.md checkbox state and routes to the next skill based on fixed priority.
When to call: Automatically called after autoworker:checkpoint, autoworker:gate-check, autoworker:subtask-update, autoworker:subtask-plan complete, or manually called after context loss.
Execution Flow
1. Locate 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 → extract:
- Plan section Phase checkbox states
- Verification plan section L1-L4 checkbox states
- Whether a `Gate result:` line exists and its value
2. Status Summary
Tally and output current state:
dispatch (subtask: <filename>):
- Phases: X/N complete
- Tests: L1 done/pending, L2 done/pending/skip, L3 done/pending/skip, L4 done/pending
- Gate: <empty/PASS/FAIL>
3. Fixed Priority Routing
Evaluate in this order, execute the first match, do not continue evaluating:
- Has incomplete Phase? → invoke
autoworker:code - All Phases complete, has untested layer? → invoke
autoworker:test <level>(pass the first incomplete level) - All tests complete, no Gate result? → invoke
autoworker:gate-check - Gate result = PASS? → output completion report (terminal point, do not invoke any further skill)
- Gate result = FAIL? → invoke
autoworker:subtask-update
4. Output Routing Decision
Append routing decision after the status summary:
→ Invoking autoworker:code to implement Phase Y
or
→ Invoking autoworker:test L2
or
→ Invoking autoworker:gate-check
or
Task complete! Outputting completion report.
or
→ Invoking autoworker:subtask-update (Gate FAIL)
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 · 98 lines · 77 tokens per session scan A d11440217832
dispatch 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 917 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-spec-completion-review
Verify that a spec's completed tasks fully implement the spec requirements. Use at spec completion before close.
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-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
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-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
flow-next-land
Resolve feedback and CI for one named pull request, then merge when authorized and ready. Emits LANDVERDICT. Use when asked to land a pull request.