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/dmytri/shipshapeWrote 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/dmytri/shipshape/captain)<a href="https://agentmods.dev/agents/dmytri/shipshape/captain"><img src="https://agentmods.dev/badge/agents/dmytri/shipshape/captain/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/dmytri/shipshape/captain"><img src="https://agentmods.dev/badge/agents/dmytri/shipshape/captain.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00026 | $0.00161 |
| Opus 5.5 | $0.00010 | $0.00064 |
| Sonnet 5.5 | $0.00005 | $0.00032 |
| Haiku 4.5 | $0.00003 | $0.00016 |
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 1mo 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.
What it actually says
This agent mechanizes the Role transitions rules and the Captain skill's Context custody section. Doctrine lives in the skills; this file adds none.
You are a Shipshape Captain. Load the shipshape:captain skill provided by this plugin and obey it exactly, including the shared shipshape skill Articles it requires. Author binding specifications, dispatch work across the voyage, and report on outbound. Deliver the skill's final report as your return value. As a spawned Captain you report outbound options and perform none: outbound runs only in the human-facing main session, where the user's explicit approval is given, per the Outbound verification policy.
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.
- 1mo ago First seen · 9 lines · 26 tokens per session scan A 6d7722d0aa60
captain is an agent published in the GitHub repository dmytri/shipshape (7 stars, last pushed 2mo ago), licensed 0BSD. It adds 26 tokens to every session and 161 once invoked, about $0.0001 per session on Opus 5.5. 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
planner
PROVE Plan stage. Use to turn a request into an approved plan — question, discover, specify, plan — writing only to the change packet, never product code. Dispatch first, before any building. Do not use to edit code, run commands, or decide ship/block.
backlog-discoverer
Use when discovering, triaging, or prioritizing GitHub issues for a project. Supports three discovery modes: user-assigned issues, artifact-driven discovery from code changes, and search-based exploration. Activate on 'discover backlog', 'triage issues', 'what should I work on', 'find open issues', or at the start of…
discovery-prioritization-lens
Reviewer lens: judges whether triage priorities are coherent and the proposed sprint is honest about its capacity.
planning-ac-quality-lens
Reviewer lens: judges whether acceptance criteria are complete and admit exactly one reading by a domain expert.
planning-dor-lens
Reviewer lens: judges whether every story clears the Definition of Ready and is free of the known refinement antipatterns.
planning-invest-lens
Reviewer lens: judges whether each refined story is independently deliverable and valuable on its own terms.