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/verifying-wave-completionnpx skills add Acendas/shipyard --skill verifying-wave-completiongit clone --depth 1 https://github.com/Acendas/shipyardWrote 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/acendas/shipyard/verifying-wave-completion)<a href="https://agentmods.dev/skills/acendas/shipyard/verifying-wave-completion"><img src="https://agentmods.dev/badge/skills/acendas/shipyard/verifying-wave-completion.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.02155 |
| Opus 5 | $0.00007 | $0.01077 |
| Sonnet 5 | $0.00003 | $0.00431 |
| Haiku 4.5 | $0.00001 | $0.00215 |
Grade A, and why
verifying-wave-completion 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying Wave Completion
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.
A passing wave-scoped probe is necessary but not sufficient. The wave is fully complete only when six invariants hold simultaneously. This capability skill runs that composite check after the existing wave-boundary steps (rebase + ff-merge, wave-scoped build, REFACTOR + MUTATE, wave-scoped tests, wave VERIFY) and gates advance-to-next-wave on the result.
The check exists because the structured return contract makes false completion structurally hard at the subagent boundary, but the wave boundary is one level up — and pre-this-skill, the only gate there was a single probe pass. A flaky test, a dropped commit, or a subagent that exited mid-flight without writing its completion event could all slip through.
When to Invoke
/ship-execute Step 4 calls this skill as the final gate before advancing the wave counter, AFTER the existing in-line checks have all reported green. Job: confirm the composite picture matches the per-step verdicts.
Other entry points:
/ship-reviewStage 1 (sprint-level) may invoke this as a per-wave audit when re-running review on an archived sprint.- Manual invocation when a user wants to confirm a specific wave is truly complete before advancing.
Inputs
wave_number— e.g.,2task_ids— list of task IDs dispatched in this wave, e.g.,["T-042", "T-043", "T-044"]data_dir— literal<SHIPYARD_DATA>pathworking_branch— git branchwave_base_sha— working-branch HEAD BEFORE the wave started (set by/ship-executeat wave entry)wave_head_sha— working-branch HEAD AFTER the wave's merges (set after the rebase + ff-merge step)wave_probe_capture— path to the wave-scoped test capture filewave_probe_exit_code— exit code from the wave-scoped test runwakeup_budget— number of recovery wakeups before escalation. Default3.wakeup_delay_seconds— delay per wakeup. Default180(warm-cache window — see schedule-wakeup-discipline.md).
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 132 lines · 14 tokens per session scan A 3dc5478fccbc
verifying-wave-completion is a skill published in the GitHub repository Acendas/shipyard (2 stars, last pushed 23d ago), licensed MIT. It adds 14 tokens to every session and 2,155 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
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.
pr-review-expert
Professional Pr Review Expert skill. Orchestrate technical collaboration, design reviews, sprint planning, and system diagnostics.
issue-triage
Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.
batch-all-issues
Resolve every open issue one at a time: fact-check each with web research, close the ones that need no action, and run the goal-pr skill to fix, review, and merge the ones that do — repeating until no actionable issues remain.
moai-kanban-foreman
One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…