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/Houseofmvps/ultrashipWrote 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/commands/houseofmvps/ultraship/ship)<a href="https://agentmods.dev/commands/houseofmvps/ultraship/ship"><img src="https://agentmods.dev/badge/commands/houseofmvps/ultraship/ship/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/commands/houseofmvps/ultraship/ship"><img src="https://agentmods.dev/badge/commands/houseofmvps/ultraship/ship.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 | $0.00011 | $0.00683 |
| Opus 5 | $0.00005 | $0.00342 |
| Sonnet 5 | $0.00002 | $0.00137 |
| Haiku 4.5 | $0.00001 | $0.00068 |
Grade A, and why
ship 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ship — Pre-Deploy Quality Gate
Run all Ultraship auditors in parallel and produce a screenshot-shareable scorecard.
What It Runs
5 scored categories from 6 tools, all in parallel:
| Category | Tools | What it checks |
|---|---|---|
| SEO + AI Visibility | seo-scanner | 39 SEO rules (meta tags, headings, OG tags, canonicals, cross-page analysis) + 20 GEO rules (AI bot access, snippet restrictions) + 4 AEO rules (schema checks) |
| Accessibility | a11y-scanner | WCAG 2.2 A/AA static checks: missing alt text, unlabeled form controls, icon-only buttons, missing lang, heading order, positive tabindex, zoom disabled, broken aria references |
| Security | secret-scanner | AWS keys, Stripe keys, GitHub tokens, private keys, DB URLs, JWT secrets in source files |
| Code Quality | code-profiler + dep-doctor | N+1 queries, sync I/O in handlers, memory leaks, unbounded queries, unused/outdated dependencies |
| Bundle Size | bundle-tracker | Build output size, heavy dependency detection (moment→dayjs, lodash→native, axios→fetch) |
How to Run
In Claude Code:
/ship
Standalone CLI:
npx ultraship ship .
npx ultraship ship /path/to/project
Scoring
- Each category starts at 100, deducts per finding based on severity
- SEO deduplicates by rule (same issue on N pages = one deduction)
- Failed tools show as
FAILand are excluded from the overall average - Overall = average of categories that successfully ran
Status thresholds:
-
= 80: READY TO SHIP
- 60-79: NEEDS WORK
- < 60: NOT READY
After the Scorecard
The scorecard tells you what's wrong. To fix issues:
- Run individual audit commands for detailed findings:
ultraship seo .— full SEO findings with file:line locationsultraship a11y .— all WCAG 2.2 accessibility findingsultraship security .— all detected secretsultraship profile .— N+1 queries, sync I/O, memory leaksultraship deps .— unused and outdated packages
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.
- 9d ago First seen · 70 lines · 11 tokens per session scan A 763bd6c2a006
ship is a command published in the GitHub repository Houseofmvps/ultraship (121 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 683 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 2026-08-30.
Other commands, from other repositories
version-bump
Bump versions across the monorepo during release process.
ship
Complete PR workflow from commit to production with validation.
sprint
Sprint lifecycle — plan a sprint, run a retrospective, or generate release notes.
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
ia-changelog
Create engaging changelogs for recent merges to main branch.
commit
Create well-formatted commits with conventional commit messages and emojis.