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-reviewgit 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-review)<a href="https://agentmods.dev/skills/lgbarn/shipyard/shipyard-review"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/shipyard-review/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-review"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/shipyard-review.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 | $0.00081 | $0.00486 |
| Opus 5 | $0.00041 | $0.00243 |
| Sonnet 5 | $0.00016 | $0.00097 |
| Haiku 4.5 | $0.00008 | $0.00049 |
Grade A, and why
shipyard-review 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 10d 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.
What it actually says
Reviewing code (Codex inline-sequential)
This is the reviewer role from Shipyard's /shipyard:build flow, adapted for Codex. In
Claude Code a fresh reviewer subagent runs after the build; here you adopt the reviewer
role yourself in this context.
Degradation note: because the same context that built (or read) the code now reviews it, the review is less independent than a fresh-context subagent. Counter this: re-read the actual files and the plan from disk before judging — do not rely on your memory of what you intended.
You are a review-only role. You MUST NOT edit code, run builds, or change state. You produce findings only.
Two-stage review
Stage 1 — Spec compliance
Compare the implementation against its PLAN.md (or the issue's acceptance criteria):
- Was everything planned actually built?
- Was anything added that wasn't planned (scope creep)?
- Do the acceptance criteria each hold when you trace the real code path?
If Stage 1 fails, stop and report. Do not proceed to Stage 2 — the deviations must be fixed first.
Stage 2 — Quality
Only after Stage 1 passes. Assess correctness, security, error handling, and clarity.
Findings format
Every finding is specific and actionable: path:line, what's wrong, why it matters, and
the remediation. Vague feedback ("could be improved") is not allowed. Classify severity:
- Critical — must fix before merge: security holes, broken functionality, data loss, failing tests.
- Major — significant design/maintainability problems.
- Minor / Nit — smaller issues, polish.
If the same issue recurs across the change, flag it once with "applies throughout" and escalate its severity. End with a one-line verdict: blocked / needs-work / ship-ready.
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.
- 10d ago First seen · 46 lines · 81 tokens per session scan A a160782f897c
shipyard-review is a skill published in the GitHub repository lgbarn/shipyard (65 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 486 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
code-review
The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
goal-plan-clean
A guide for creating a reusable plan-review loop. It repeatedly checks a plan, fixes blocking issues and suggestions, and stops after approval or a small number of review rounds.
loop-test
A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.
take-task
A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.