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 skills add lgbarn/shipyard --skill shipyard-shipgit clone --depth 1 https://github.com/lgbarn/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/lgbarn/shipyard/shipyard-ship)<a href="https://agentmods.dev/skills/lgbarn/shipyard/shipyard-ship"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/shipyard-ship/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lgbarn/shipyard/shipyard-ship"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/shipyard-ship.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00086 | $0.00547 |
| Opus 5.5 | $0.00034 | $0.00219 |
| Sonnet 5.5 | $0.00017 | $0.00109 |
| Haiku 4.5 | $0.00009 | $0.00055 |
Grade A, and why
shipyard-ship 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 1mo 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shipping a phase (Codex inline-sequential)
This is Shipyard's /shipyard:ship delivery flow, adapted for Codex. The flow is already
sequential (verify → audit → document → deliver), so it maps cleanly to a single context —
you adopt each role in turn rather than dispatching subagents.
Degradation note: the audit and documentation steps run as inline personas, not fresh-context subagents. Be deliberately thorough on the audit step — shipping is the final gate, so do not let earlier context make you assume the code is fine.
Run scripts/state-read.sh first if state isn't loaded.
Steps (run each in order; stop on a hard failure)
- Pre-ship verification. Use the
shipyard-verificationskill to confirm success criteria are met and the phase is actually complete. - Run the test suite. All tests must pass. A failure here blocks the ship.
- Pre-ship security audit. Adopt the auditor mandate (OWASP Top 10, secrets, dependency vulnerabilities). Shipping is the final security gate — this runs even if the build skipped auditing. If a passing audit already exists and nothing changed since, verify it has no unresolved critical findings instead of re-auditing. Any unresolved critical finding blocks the ship.
- Documentation. Adopt the documenter mandate — generate/refresh API, architecture, and
user-facing docs in
docs/. If up-to-date docs already exist from the build, verify completeness instead of regenerating. - Capture lessons. Use the
lessons-learnedskill to record what was learned this phase. - Deliver. Finalize per the project's release convention (version bump, CHANGELOG, tag, PR/merge). Never auto-merge without the user's go-ahead unless they've authorized it.
Done means
Verification passed, tests green, no unresolved critical audit findings, docs complete, lessons captured, and the release artifact prepared. Report the status of each gate explicitly — do not claim "shipped" if any gate was skipped.
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.
- 1mo ago First seen · 40 lines · 86 tokens per session scan A ae84f269cd41
shipyard-ship is a skill published in the GitHub repository lgbarn/shipyard (65 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 547 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
pr
Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.
pr-threads-address
Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.
pr-comment
Post friendly review comments to a GitHub PR — prepare locally, preview, then submit as atomic review. Use when: posting code review comments, giving PR feedback, sending inline suggestions. Not for: reading existing reviews (use load-pr-review), creating PRs (use create-pr), PR status (use pr-summary).
deploy-landed
A deployment verification procedure that checks whether the intended code revision is actually running, its environment settings are present, and the product works. A deployment is the process of putting new software on a server or hosting platform.
signing-preflight
Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…