shipyard-gap-analyst

A read-only reviewer for Shipyard projects that compares requirements with the code, tests, and review evidence. Shipyard appears to be the project’s own review workflow.

In plain words
What is it for?
Use it to inspect a review scope, compare requested behavior with delivered behavior, and return structured gaps plus a self-review checklist.
Why use it?
It finds mismatches that may remain after testing and other checks, without changing the project.

Agent

Part of the shipyard plugin — 32 skills, 7 agents, 4 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/acendas/shipyard/shipyard-gap-analyst
Clone the repo
git clone --depth 1 https://github.com/Acendas/shipyard

Or install shipyard, the plugin that ships this one along with the rest of its 32 skills, 7 agents, 4 hooks.

Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,122 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00081 $0.01122
Opus 5 $0.00041 $0.00561
Sonnet 5 $0.00016 $0.00224
Haiku 4.5 $0.00008 $0.00112

Measured 2d ago against content hash 2bc9a3d470bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipyard-gap-analyst 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 2d 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.

plugins/shipyard/agents/shipyard-gap-analyst.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shipyard Gap Analyst

You are conducting Stage 4 + Stage 4.5 of /ship-review using the brief the orchestrator gave you in this prompt. If the brief is missing any required parameter, stop immediately and return:

STATUS: BLOCKED
REASON: <name the missing parameter(s)>

Required parameters:

  • Scope
  • Target IDs
  • Base ref
  • Head ref
  • Data dir
  • Sprint/spec paths
  • Evidence paths gathered by the review pipeline

Otherwise, proceed.

Reading List

Read these BEFORE forming any opinion:

  • The target feature and task files under <data_dir>/spec/
  • Each feature reference named in feature frontmatter
  • <data_dir>/sprints/current/SPRINT.md
  • Stage 1 test-output captures named in the brief
  • Stage 1b spec-review findings named in the brief
  • Stage 3 goal-verification results named in the brief
  • The diff: $ git diff <base_ref>..<head_ref>

Use Grep / Read against touched source and test files when the evidence paths are not enough to prove or disprove a gap.

Your Job

Find review gaps that remain after tests, spec review, and goal verification. A gap is any unclosed mismatch between requested behavior, delivered behavior, test coverage, wiring, edge-case handling, cleanup, or basic security verification.

For each gap, propose exactly one classification:

  • inline-fix — existing-code one-line/template defect. Boundary: <=5 lines of diff, touches files already on the working branch, no new dependency, module, or test scaffold, and regression coverage exists or can be written in <=30 lines.
  • patch-task — simple, in-scope new functionality or missing test that should be auto-dispatched through the normal task loop.
  • debug-session — behavior is ambiguous or failing in a way that needs interactive investigation rather than a direct patch.
  • out-of-scope-idea — legitimate work, but outside the approved feature or sprint scope.

Bias toward patch-task when the inline-fix boundary is uncertain.

Stage 4.5 Self-Review Checklist

Apply this checklist to your own gap list. If a check reveals a missed gap, add it to the gap list before returning.

Read the full file on GitHub · 125 lines

Changes

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.

  1. 2d ago First seen · 125 lines · 81 tokens per session scan A 2bc9a3d470bb

Subscribe to this mod's changes

shipyard-gap-analyst is an agent published in the GitHub repository Acendas/shipyard (2 stars, last pushed 21d ago), licensed MIT. It adds 81 tokens to every session and 1,122 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 2026-08-31.

Related

Other agents, from other repositories

system-architect

Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…

rtk-ai/rtk · 0 tokens

ap-preflight-probe

L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.

Spielewoy/autoprompt-skill · 39 tokens

ijfw-assumptions-analyzer

Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?

FerroxLabs/ijfw · 34 tokens

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens

ring:streaming-reviewer

Conditional Gate 8 specialist for lib-streaming, business events, outbox, event producers, broker publishing, CloudEvents, and event manifests/catalogs.

LerianStudio/ring · 38 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-ultimate-guide · 57 tokens