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/ship-debugnpx skills add Acendas/shipyard --skill ship-debuggit 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 | $0.00012 | $0.04550 |
| Opus 5 | $0.00006 | $0.02275 |
| Sonnet 5 | $0.00002 | $0.00910 |
| Haiku 4.5 | $0.00001 | $0.00455 |
Grade A, and why
ship-debug 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shipyard: Persistent Debugger
Systematic debugging that doesn't lose progress when context compacts or sessions break.
Context
!shipyard-context debug-session
Paths. All file ops use the absolute SHIPYARD_DATA prefix from the context block. No ~, $HOME, or shell variables in file_path. Bash invocation of shipyard-data is limited to the onboarding command surfaced by context plus the lock check/lock acquire/lock release subcommands (see Step 4's mutex checks), and shipyard-context reads — no other shell-out; use Read / Grep / Glob for everything else. Never use echo/printf/shell redirects to write state files — use the Write tool (auto-approved for SHIPYARD_DATA).
Onboarding gate. If the bundled context contains SHIPYARD_ONBOARDING_REQUIRED=true, run the exact SHIPYARD_ONBOARDING_COMMAND once with Bash, report the CLI output to the user, and STOP. Do not infer setup state by reading or writing Shipyard state files; onboarding decisions are CLI-owned.
Render before asking. Before every AskUserQuestion, render the decision context — the scenarios, concrete examples, tradeoffs, and any verbatim content being approved — as chat text; the tool call then carries only the short question and option labels. A bare AskUserQuestion with no rendered context above it is a bug (the window is too small to carry a real decision). Content that exists only in a Read result, a subagent/Agent return, a dossier file, or the question/option strings themselves does not count as rendered (the UI shows a compact card) — restate it as assistant chat text immediately above the ask.
Quiet by default. Between user-input gates, work quietly — investigate, run captures, and update the debug file without narrating each hypothesis-test in chat (the debug file is the record; that's where the running log lives, not the conversation). Only a one-line transition marker per boundary (status change, hypothesis eliminated) reaches the chat between gates. The diagnosis, fix plan, and resolution are rendered in full ONLY at a gate (render-before-ask — Step 3.5 fix plan, Step 6 close) or when the fix-attempt escalation fires. No running commentary ("Now I'll…", "Let me…", explaining a no-input step). Full doctrine: ${CLAUDE_PLUGIN_ROOT}/skills/ship-discuss/references/communication-design.md § "Interim Communication: Quiet by Default".
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 · 298 lines · 12 tokens per session scan A 2f48c26650f7
ship-debug is a skill published in the GitHub repository Acendas/shipyard (2 stars, last pushed 20d ago), licensed MIT. It adds 12 tokens to every session and 4,550 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.