ship-critic

A rubric-based evaluator that gives deliverables a PASS or REVISE decision before a workflow can continue. A rubric is a fixed checklist used to judge quality.

In plain words
What is it for?
It is for scoring Ship Engine deliverables, checking consistency across a run, selecting rubrics, and evaluating specific stages or gates.
Why use it?
It blocks incomplete or inconsistent work from moving to the next approval stage.

Skill for Claude CodeCodex

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 skills/maxtechera/ship/critic
Any agent
npx skills add maxtechera/ship --skill critic
Clone the repo
git clone --depth 1 https://github.com/maxtechera/ship

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,881 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 $0.00026 $0.01881
Opus 5 $0.00013 $0.00941
Sonnet 5 $0.00005 $0.00376
Haiku 4.5 $0.00003 $0.00188

Measured 2d ago against content hash c8aa2baaa6f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ship-critic 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.

supervisors/critic/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship Critic — Self-Sufficient Evaluator

Deterministic evaluation contract for Ship Engine. A supervisor (or evaluator agent) runs this logic by following this document and the rubric files — no Python required.

Decision lock: critic runs before every gate and before any deliverable can move to verified. REVISE blocks advancement unless a valid override is present.


Invocation Contract

Argument Description
--ticket <ID> Linear ticket identifier to evaluate
--stage <stage> Stage name for rubric lookup in deliverable mode (validate, strategy, awareness, lead-capture, nurture, closing, launch, measure)
--deliverable <type> Artifact key being checked (validation_report, icp, ship_plan, etc.)
--run-id <ID> Parent run ticket identifier (required for cross-check)
--gate <gate> Gate mode selector (gate-v, gate-s, gate-l)
--cross-check Run full cross-deliverable consistency review for the run
--list-rubrics List available rubric names from supervisors/critic/rubrics/*.md

Mode selection

  • --list-rubrics only: print rubric names and stop
  • --cross-check requires --run-id
  • --gate mode requires --ticket
  • Deliverable mode requires --ticket, --stage, and --deliverable
  • Invalid combination → return usage error

Rubric Loading Rules

Rubric directory: supervisors/critic/rubrics/

  • Deliverable mode loads rubrics/{stage}.md
  • Gate mode loads rubrics/{gate}.md (e.g., gate-v, gate-s, gate-l)
  • Cross-check mode loads rubrics/cross-check.md

Missing rubric fallbacks:

  • Deliverable mode: No specific rubric found. Check that the artifact is linked, non-empty, and uses VoC language.
  • Gate mode: Verify: (1) all hard-gate required fields present, (2) evidence links resolve, (3) kanban proof blocks complete, (4) all deliverables in this stage have critic PASS.
  • Cross-check mode: emit warning, skip with non-blocking exit.

Read the full file on GitHub · 219 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 · 219 lines · 26 tokens per session scan A c8aa2baaa6f6

Subscribe to this mod's changes

ship-critic is a skill published in the GitHub repository maxtechera/ship (2 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 1,881 once invoked, about $0.0001 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens