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 agentmods add skills/acendas/shipyard/dispatching-task-loopnpx skills add Acendas/shipyard --skill dispatching-task-loopgit clone --depth 1 https://github.com/Acendas/shipyardWhat 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 | $0.00014 | $0.06411 |
| Opus 5 | $0.00007 | $0.03206 |
| Sonnet 5 | $0.00003 | $0.01282 |
| Haiku 4.5 | $0.00001 | $0.00641 |
Grade A, and why
dispatching-task-loop 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 yesterday.
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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispatching the Task Loop
Render before asking. Before any AskUserQuestion, render the decision context as assistant chat text. Content that exists only in a Read result, a subagent/Agent return, or the question/option strings does not count as rendered (the UI shows a compact card) — restate it in chat first.
This is how Shipyard executes one task without burning the orchestrator's context window. The subagent does the loop; the orchestrator does the gate.
Why this exists. A self-checking loop's reliability is structural — the loop refuses to exit until completion is real. But running that loop in the orchestrator session means every false attempt accumulates in the orchestrator's context. By the fifth iteration, the orchestrator is operating on a summary of a summary. Move the loop into a subagent instead: the subagent absorbs every iteration's reasoning, false attempts, and tool calls; when it returns, only a structured summary lands in the orchestrator.
Goal-mode default
This loop is /goal-shaped at the task level: "work until the acceptance probe passes." There is no flag, no opt-in — the subagent's internal cycle and iteration cap (5) ARE the /goal semantics. The cap exists so the orchestrator can redirect on genuinely stuck tasks (one redispatch via the orchestrator-side rule, then needs-attention), not so the subagent can give up early. The subagent must not return STATUS: COMPLETE until the probe passes; it must not return STATUS: BLOCKED before exhausting reasonable attempts.
The orchestrator does NOT surface mid-loop to the user. Probe failures inside the iteration cap stay inside the subagent context. The user sees only the final structured return summarized by the caller: COMPLETE with evidence, or BLOCKED with a one-paragraph reason after the cap. Do not forward subagent preamble, epilogue, or incidental commentary. This is the trade /goal makes — silence between dispatch and result, with the structured return contract guaranteeing no silent false completion.
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.
- yesterday First seen · 201 lines · 14 tokens per session scan A 0b3dfee24ae7
dispatching-task-loop is a skill published in the GitHub repository Acendas/shipyard (2 stars, last pushed 20d ago), licensed MIT. It adds 14 tokens to every session and 6,411 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
engenharia-de-requisitos
Use when doing requirements engineering, business analysis, or the software-engineering stage of discovering / specifying / validating / managing requirements — the stage BEFORE code (what to build) and AFTER (was the right thing built?), for new projects and for evolutions of existing ones. Triggers (EN)…
engenharia-de-requisitos
Use when doing requirements engineering, business analysis, or the software-engineering stage of discovering / specifying / validating / managing requirements — the stage BEFORE code (what to build) and AFTER (was the right thing built?), for new projects and for evolutions of existing ones. Triggers (EN)…
write-epic
Produces a complete epic definition following Atlassian agile guidance. An epic captures a large initiative that is too big for a single sprint and must be decomposed into user stories.
write-user-story
Produces a complete, ready-to-groom user story following the standard Atlassian/agile format. It applies the INVEST criteria and the 3 Cs framework (Card, Conversation, Confirmation) to ensure each story is well-scoped, valuable, and testable — not just syntactically correct.
agentflow
Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.
backlog-grooming
Review Agiflow Planning tasks for readiness, prioritize approved work, group related tasks into work units, and promote ready tasks to Todo. Use when grooming a backlog, organizing planned tasks, creating work units, or deciding what should be executed next.