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.
npx agentmods add rules/dmytri/shipshape/shipwrightgit clone --depth 1 https://github.com/dmytri/shipshapeWhat 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 | $0.00009 | $0.00251 |
| Opus 5 | $0.00005 | $0.00125 |
| Sonnet 5 | $0.00002 | $0.00050 |
| Haiku 4.5 | $0.00001 | $0.00025 |
Grade A, and why
shipwright 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.
What it actually says
Shipwright, before reporting harbour complete:
- Read production code to discover behaviour; change no production behaviour and no verification, per the Shipwright skill.
- Plank every production seam in scope, and write
@captain-tagged skeletons for unspecified behaviour, per the "Every production seam is planked" Article. - Remove only
@shipwright-condemned scenarios and the code their steps plank, reverting when the suite reddens, per the Shipwright skill. - Derive
RIGGING.mdto the Rigging shape, and prove every derived methodology check red once with a planted violation before writing it. - Run harbour's one full regression at entry, every configured tier cheapest first through the
coveragecommand, and record weather in the wake; prove condemnation removals by scoped runs, per the Shipwright skill. - Run the verification-economy audit over the entry regression's weather, assess the five lenses per scenario, and report each finding with its lens; routing is Captain's per the Harbour flow.
Doctrine lives in skills/shipwright/SKILL.md; when this rule and the skill disagree, the skill wins.
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.
- yesterday First seen · 15 lines · 9 tokens per session scan A 49354b3c58f1
shipwright is a cursor rule published in the GitHub repository dmytri/shipshape (7 stars, last pushed 27d ago), licensed 0BSD. It adds 9 tokens to every session and 251 once invoked, about $0.0000 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.
Other cursor rules, from other repositories
agentic-loops
Use when building multi-turn agents, tool-calling systems, agent orchestration, or autonomous workflows — covers loops, tool calling, branching, reflection patterns.
handoff
Export a Waybill Bundle by default, or import one when explicitly requested.
ui-motion-workflow
Orchestrate motion-aware UI work by sequencing direction, provider choice, implementation, and browser validation.
prompt-routing
Route tasks to the correct Universal AI Engineering Prompt.
commits
Conventional Commits standards for clear, semantic commit messages.
feature
Gherkin feature file standards and BDD best practices.