Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Acendas/shipyard/plugin install 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-discuss)<a href="https://agentmods.dev/skills/acendas/shipyard/ship-discuss"><img src="https://agentmods.dev/badge/skills/acendas/shipyard/ship-discuss.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 5.1 | $0.00012 | $0.19053 |
| Opus 5 | $0.00006 | $0.09527 |
| Sonnet 5 | $0.00002 | $0.03811 |
| Haiku 4.5 | $0.00001 | $0.01905 |
Grade A, and why
ship-discuss 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 6d 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 — 769 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shipyard: Feature Discussion
You are facilitating a feature discovery conversation. This is fluid — not a questionnaire.
Context
!shipyard-context discuss-context
Paths. Use the absolute SHIPYARD_DATA prefix from the bundled context block. No ~, $HOME, or shell variables in file_path. No bash command substitution for shipyard-data or shipyard-context — use Read / Grep / Glob after context is loaded. 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.
Quiet by default. This is a conversation, so the interruption rounds carry real discussion — but between them, work quietly. Only three things reach the chat outside a user-input round: a one-line transition marker per phase, a compact ASCII diagram/status block, and a one-line banner when launching or receiving the background deep-dive (→ Deep-dive back: 3 findings, 1 data-model risk). Research findings, viability reads, impact maps, and diagrams are rendered in full ONLY when they feed an imminent AskUserQuestion (render-before-ask) — otherwise they collapse to a one-line result and fold into the eventual gate summary. Reading the dossier puts it in YOUR context; that is not a reason to re-emit it as prose unless a decision rides on it now. No running commentary ("Now I'll research…", "Let me run the viability gate…", explaining a no-input phase). Full doctrine: ${CLAUDE_PLUGIN_ROOT}/skills/ship-discuss/references/communication-design.md § "Interim Communication: Quiet by Default".
Capability-skill playbooks. Where a step says "follow the X playbook" or "dispatch X", X is a capability skill — Read ${CLAUDE_PLUGIN_ROOT}/skills/<X>/SKILL.md and execute it inline; never hand it to the Skill tool (capability skills are disable-model-invocation: true, so Skill refuses them). There is no legacy loop-skill fallback.
What ships with it
15 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.
- references/backlog-reeval.md 4.5 KB
- references/communication-design.md 25 KB
- references/discovery-techniques.md 5.4 KB
- references/epic-integration-ac.md 3.8 KB
- references/epic-mode.md 6.2 KB
- references/external-issue-fetch.md 4.5 KB
- references/impact-analysis.md 6.0 KB
- references/phase-1-5b-challenge.md 3.1 KB
- references/phase-1-research.md 12 KB
- references/phase-3-write-spec.md 9.5 KB
- references/phase-e2e-validation.md 4.6 KB
- references/phase-finalize.md 5.8 KB
- references/phase-quality-and-critique.md 10 KB
- references/question-design.md 13 KB
- references/simplification-scan.md 8.9 KB
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.
- 6d ago First seen · 769 lines · 12 tokens per session scan A 1d95ec7f7d07
ship-discuss is a skill published in the GitHub repository Acendas/shipyard (2 stars, last pushed 24d ago), licensed MIT. It adds 12 tokens to every session and 19,053 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
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
audio-production
Professional audio production for music, podcasts, and sound design. Use when working with audio recording, mixing, mastering, or sound design for any medium.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.
brand-identity
Brand strategy and identity design for businesses and products. Use when creating brand guidelines, developing visual identity systems, or defining brand positioning.