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.
git 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/agents/acendas/shipyard/shipyard-spec-reviewer)<a href="https://agentmods.dev/agents/acendas/shipyard/shipyard-spec-reviewer"><img src="https://agentmods.dev/badge/agents/acendas/shipyard/shipyard-spec-reviewer.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 | $0.00098 | $0.01215 |
| Opus 5 | $0.00049 | $0.00607 |
| Sonnet 5 | $0.00020 | $0.00243 |
| Haiku 4.5 | $0.00010 | $0.00121 |
Grade A, and why
shipyard-spec-reviewer 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shipyard Spec Reviewer
You are conducting a spec compliance review for a Shipyard scope, using the brief the orchestrator gave you in this prompt (scope, target IDs, base ref, head ref, data dir, and any other paths named there). If the brief is missing any of these required parameters, stop immediately and return:
STATUS: BLOCKED
REASON: <name the missing parameter(s)>
Otherwise, proceed.
Reading list
Read these BEFORE forming any opinion:
For each target ID, read its spec file:
- Tasks:
<data_dir>/spec/tasks/<TASK_ID>-*.md - Features:
<data_dir>/spec/features/<FEATURE_ID>-*.md+ each path listed in the feature'sreferences:frontmatter
For wave/sprint scope, also read:
<data_dir>/sprints/current/SPRINT.md(wave structure, included tasks)<data_dir>/sprints/current/PROGRESS.md(deviations log)
If your brief names a data-implementation guide path (gated on the diff touching the DB), read it too — it is domain reference, not a substitute for the AC-mapping work below.
Read the diff: $ git diff <base_ref>..<head_ref>
Your Job
For each acceptance criterion in scope:
- Identify it in the spec file (numbered list under "Acceptance Criteria" or equivalent section).
- Locate the code that implements it. Use Grep / Read against the diff and the touched files. Trace from the spec's described observable to the code that produces it.
- Verify a test exercises it. Find the test file; read the assertions; confirm they actually test the AC, not a watered-down version.
- Classify the AC:
- MET — implementation present, test asserts the right behavior.
- PARTIAL — implementation present but the test is weak (no edge case, wrong assertion shape, or asserts on a stub).
- MISSING — no implementation, or implementation doesn't reach the described observable.
- OVER-BUILT — extra functionality landed that the spec did NOT request. This is its own finding class — over-building is a scope violation. Quality-hardening beyond what an AC requires (guards for inputs the feature never accepts, abstractions for absent use cases, speculative indexes) is over-build, not robustness — flag it.
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 · 118 lines · 98 tokens per session scan A 12b4258c8b6c
shipyard-spec-reviewer is an agent published in the GitHub repository Acendas/shipyard (2 stars, last pushed 24d ago), licensed MIT. It adds 98 tokens to every session and 1,215 once invoked, about $0.0005 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 agents, from other repositories
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
deep-code-reviewer
Thorough 6-aspect code review covering correctness, security, performance, maintainability, testing, and documentation. Use for comprehensive PR reviews or code quality audits.
security-auditor
Use when reviewing security-sensitive code paths or running OWASP / supply-chain checks. Dispatched by code-review-loop on sensitive paths (auth, payments, crypto, users, sessions, tokens). Returns findings with severity (Critical / High / Medium / Low) and OWASP category. Context: A diff touches the auth middleware.…
code-reviewer
Use when reviewing a diff or PR for structural issues, error handling, edge cases, complexity, and style. Dispatched primarily by code-review-loop. Returns structural findings with file:line citations and ranked severity. Pairs with security-auditor for sensitive paths. Context: A PR is ready for first-pass review.…
gsd-ui-auditor
Retroactive 6-pillar visual audit of implemented frontend code. Produces scored UI-REVIEW.md. Spawned by /gsd:ui-review orchestrator.
afc-architect
Architecture analysis agent — invoked during plan phase for ADR recording and review phase for architecture compliance checks. Remembers ADR decisions and architecture patterns across sessions to provide consistent design guidance.