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-backlognpx skills add Acendas/shipyard --skill ship-backloggit 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/ship-backlog)<a href="https://agentmods.dev/skills/acendas/shipyard/ship-backlog"><img src="https://agentmods.dev/badge/skills/acendas/shipyard/ship-backlog.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 | $0.00012 | $0.04772 |
| Opus 5 | $0.00006 | $0.02386 |
| Sonnet 5 | $0.00002 | $0.00954 |
| Haiku 4.5 | $0.00001 | $0.00477 |
Grade A, and why
ship-backlog 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 3d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shipyard: Backlog Manager
Manage the prioritized backlog. Default sort is by RICE score (Reach x Impact x Confidence / Effort — higher means more valuable).
Data model: BACKLOG.md is an ordered index of feature IDs. All feature data (title, RICE, points, status, complexity) is read from feature files on display. Never duplicate feature data into BACKLOG.md. See ${CLAUDE_PLUGIN_ROOT}/project-files/rules/shipyard-data-model.md (rules live in the plugin in 2.0).
Context
!shipyard-context backlog-context
Paths. All file ops use the absolute SHIPYARD_DATA prefix from the context block. No ~, $HOME, or shell variables in file_path. Bash is for shipyard-context (reads) and shipyard-data feature|backlog|idea ... (state mutations) ONLY — no other shell. Never use echo/printf/shell redirects to write state files — use the Write tool (auto-approved for SHIPYARD_DATA). Never hand-Edit feature-file frontmatter or BACKLOG.md IDs/last_groomed — those are CLI-owned (feature set, feature set-status, backlog add|remove|rank|set). Feature/epic bodies and the BACKLOG.md Overrides section remain Edit-tool surface.
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.
Execution rules (load-bearing):
- Do every read yourself with Read/Grep/Glob. NEVER dispatch a subagent (Agent/Explore/Task) to gather board data. Data gathered in a subagent never lands in this context, and the board cannot be rendered from data you do not hold. (Incident 2026-07-21: a delegated gather produced a blind AskUserQuestion with no board rendered.)
- Render before asking. Render the full board as text output BEFORE the first AskUserQuestion. The ask at the end of the board is the ONLY entry into the interactive loop; an AskUserQuestion with no board above it is always a bug. Board data existing only in a Read result, a subagent return, or the question/option strings does not count as rendered (the UI shows a compact card) — only assistant chat text above the ask does.
- Quiet by default. The board and the drill-down/grooming summaries ARE the render-before-ask content — render those in full. But between them, work quietly: read feature files, stage grooming decisions, and run
shipyard-datamutations without narrating each read or each staged change. Surface a one-line result after a batch of mutations (→ Applied: 3 reprioritized, 1 archived), not a play-by-play. No running commentary ("Now I'll read F004…", "Let me check the next one…"). 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.
- 3d ago First seen · 277 lines · 12 tokens per session scan A 17e668094730
ship-backlog is a skill published in the GitHub repository Acendas/shipyard (2 stars, last pushed 22d ago), licensed MIT. It adds 12 tokens to every session and 4,772 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.
code-reviewer
Professional Code Reviewer Expert skill. Orchestrate technical collaboration, design reviews, sprint planning, and system diagnostics.
pr-review-expert
Professional Pr Review Expert skill. Orchestrate technical collaboration, design reviews, sprint planning, and system diagnostics.
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…
agent-phase-closeout
中文阶段收尾技能。用于完成一个阶段、准备开新对话、需要更新状态快照、冻结模块、整理已完成任务和下一步任务时。触发语包括"阶段收尾""帮我收工""准备开新对话""更新快照""冻结阶段""总结当前状态"。.