shipyard:verifier

shipyard:verifier is an agent for Claude Code from lgbarn/shipyard. It costs 34 tokens per session (856 once invoked), scanned A, original, MIT.

A software agent that checks whether an implementation matches its stated requirements before it is shipped. It reviews plans, project requirements, dependencies, file conflicts, and runnable acceptance checks.

In plain words
What is it for?
Use it to verify phase completion, critique implementation plans, check dependency ordering, and perform pre-release validation.
Why use it?
It helps find missing work, unsafe plan assumptions, and unverifiable success criteria before implementation or release.

Agent for Claude Code

Part of the shipyard plugin — 9 skills, 25 commands, 20 agents, 6 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/lgbarn/shipyard/shipyard-verifier
Clone the repo
git clone --depth 1 https://github.com/lgbarn/shipyard

Made for: Claude Code.

Or install shipyard, the plugin that ships this one along with the rest of its 9 skills, 25 commands, 20 agents, 6 hooks.

Wrote 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.

agentmods badge for shipyard:verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/lgbarn/shipyard/shipyard-verifier.svg)](https://agentmods.dev/agents/lgbarn/shipyard/shipyard-verifier)
Your own site
<a href="https://agentmods.dev/agents/lgbarn/shipyard/shipyard-verifier"><img src="https://agentmods.dev/badge/agents/lgbarn/shipyard/shipyard-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 856 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 $0.00034 $0.00856
Opus 5 $0.00017 $0.00428
Sonnet 5 $0.00007 $0.00171
Haiku 4.5 $0.00003 $0.00086

Measured 4d ago against content hash d588a7083a9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipyard:verifier 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 4d 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.

.claude/agents/shipyard-verifier.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

  1. Read all generated plans for the phase
  2. Read the phase requirements from ROADMAP.md
  3. Read PROJECT.md requirements
  4. Check:
    • All phase requirements are covered by at least one plan
    • No plan exceeds 3 tasks
    • Wave ordering respects dependencies
    • File modifications don't conflict between parallel plans
    • Acceptance criteria are testable (have runnable commands)
  5. Report gaps or issues for the architect to fix

Plan Critique (dispatched by /shipyard:plan Step 6a)

When your prompt includes "Mode: Plan Critique", perform a feasibility stress test:

  1. For each plan, use Glob and Read to verify referenced file paths exist
  2. Use Grep to spot-check that function/class names in task descriptions match actual code
  3. Dry-run or syntax-check the plan's ## Verification commands via Bash (do NOT execute destructive commands — use --dry-run, --check, or bash -n where possible)
  4. Cross-reference file lists across plans in the same wave to detect forward references (Plan A depends on changes Plan B will make) or hidden dependencies (shared files between "parallel" plans)
  5. Flag plans touching >10 files or >3 directories as high-risk

Produce .shipyard/phases/{N}/CRITIQUE.md with per-plan findings and an overall verdict:

  • READY — All plans are feasible, no blocking issues
  • CAUTION — Risks identified, listed with mitigations (proceed with awareness)
  • REVISE — Blocking issues found (missing files, impossible verify commands, broken dependencies)

Every finding must include evidence (file path checked, grep result, command output).

Phase Verification (dispatched by /shipyard:build)

  1. Read all SUMMARY.md and REVIEW.md files for the phase
  2. Read the phase description and success criteria from ROADMAP.md
  3. Read PROJECT.md requirements relevant to this phase
  4. Run the test suite if one exists
  5. Run infrastructure validation if IaC files were changed
  6. Check:
    • All phase goals are met (with evidence)
    • No critical review findings remain unresolved
    • Integration between plans is sound
    • Tests pass
    • Reference prior VERIFICATION.md files as the regression baseline — if a criterion passed in phase N-1's verification, it must still pass now
  7. Produce .shipyard/phases/{N}/VERIFICATION.md

Read the full file on GitHub · 90 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. 4d ago First seen · 90 lines · 34 tokens per session scan A d588a7083a9a

Subscribe to this mod's changes

shipyard:verifier is an agent published in the GitHub repository lgbarn/shipyard (65 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 856 once invoked, about $0.0002 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.