captain

Rules for the Captain role in the Shipshape workflow. They define which project files Captain may manage, how work is handed to the Quartermaster, and what must be checked before sending results out.

In plain words
What is it for?
Use them when writing feature specifications or referenced assets, dispatching Quartermaster work, reviewing Captain-tagged scenarios, managing watchbills, and preparing an approved outbound result.
Why use it?
They prevent workflow roles from editing the wrong files or passing incomplete work between stages. They also set requirements for approval, review, and verification before delivery.

Cursor rule

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 rules/dmytri/shipshape/captain
Clone the repo
git clone --depth 1 https://github.com/dmytri/shipshape
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 226 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 $0.00011 $0.00226
Opus 5 $0.00005 $0.00113
Sonnet 5 $0.00002 $0.00045
Haiku 4.5 $0.00001 $0.00023

Measured yesterday against content hash 4e8a1cbea056, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

captain 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 yesterday.

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.

rules/captain.mdc · 14 lines

What it actually says

Captain, before dispatching or returning:

  • Write only Captain-custodied durable artifacts: .feature specs, referenced assets/**, CAPTAIN.md, and optional watchbill.json, per the "Write scopes are strict" Article.
  • Dispatch thin to QM in clear context: role and base commit; watchbill.json at its home is the only channel that creates QM targets, per the dispatch contract and the Watchbill policy.
  • Review @captain skeletons in harbour: promote by removing the tag, or discard by retagging @shipwright; unresolved @captain scenarios do not block resuming the voyage.
  • Strike a spent watchbill.json; absent at rest is the healthy state, per the Watchbill policy.
  • Outbound needs a clean Boatswain report and explicit user approval, in the human-facing main session, per the Outbound verification policy.

Doctrine lives in skills/captain/SKILL.md; when this rule and the skill disagree, the skill wins.

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. yesterday First seen · 14 lines · 11 tokens per session scan A 4e8a1cbea056

Subscribe to this mod's changes

captain is a cursor rule published in the GitHub repository dmytri/shipshape (7 stars, last pushed 27d ago), licensed 0BSD. It adds 11 tokens to every session and 226 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.