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 skills add OneWave-AI/open-agent-stack --skill ship-itgit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote 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/skills/onewave-ai/open-agent-stack/ship-it)<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/ship-it"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/ship-it/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/skills/onewave-ai/open-agent-stack/ship-it"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/ship-it.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 | $0.00053 | $0.00504 |
| Opus 5.5 | $0.00021 | $0.00202 |
| Sonnet 5.5 | $0.00011 | $0.00101 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
ship-it 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
Ship It
The gap between "works on my machine" and "live without incident" is a checklist, not luck. Run the pre-flight, fix what it catches, deploy, verify live.
Workflow
- Secrets sweep. Grep the repo for keys, tokens, and connection strings in source or committed
.envfiles. Anything found: move to env vars, rotate the exposed value (it is burned the moment it was committed), confirm.env*is gitignored. Verify everyNEXT_PUBLIC_variable is genuinely safe to be public. - Env parity. Diff
.env.localagainst what the code actually reads (process.env.sweep). Every variable the app needs gets set in Vercel before deploy -- the classic day-one failure is the env var that only exists on the laptop. - Honesty check. Production build passes locally (
npm run build-- not just dev mode), no route returns mock data pretending to be real, API routes that mutate anything have auth checks, and forms actually submit somewhere (the deployed-with-a-dead-contact-form classic). - Deploy. Push, deploy to Vercel, set the domain if provided, confirm HTTPS. Then verify LIVE, not local: walk the money path on the production URL, check a mobile viewport, confirm OG image and title render in a link preview.
- Day-one instrumentation. Analytics wired (whatever the user runs -- Vercel Analytics minimum), error visibility on (at least Vercel's runtime logs reviewed once post-deploy), and the deploy summary written: URL, what shipped, known gaps, the rollback command.
Rules
- A committed secret is a rotated secret -- no exceptions, no "it's a private repo."
- Verify on the production URL; localhost passing proves nothing about env vars, domains, or edge behavior.
- Ship with known gaps listed, never with known gaps hidden -- "search is stubbed" in the summary is fine; discovering it live is not.
- If the build fails, the answer is fixing the build, never
--forceor skipping typecheck to get the deploy through.
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 · 24 lines · 53 tokens per session scan A 2aafc4212b99
ship-it is a skill published in the GitHub repository OneWave-AI/open-agent-stack (5 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 504 once invoked, about $0.0002 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 skills, from other repositories
publish-site
Versioned site deploys to GitHub/Cloudflare/Netlify Pages.
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
git-story-film
Direct an animated film of about two minutes from a software repository's Git history. Select real commits, releases and reverts; develop the story, character and visual style; build an outline, cast sheet, storyboard and HTML review studio; then render a 4K/60fps MP4 after approval. Use for repository or product…
ship
Commit, push, create PR(s), and auto-finalize — full automation pipeline. Handles uncommitted changes and recently created PRs.
promote-release
Prepare a release on develop and promote it to main on a git-flow repo. Confirm the auto-merging release-please PR landed on develop, validate the promotion, and merge develop to main with a merge commit; release-please tags on promotion. Refuses on trunk repos (default branch main) — use /merge-pr instead.