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 skills/artttj/rapid-stack/shipnpx skills add artttj/rapid-stack --skill shipgit clone --depth 1 https://github.com/artttj/rapid-stackWhat 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 | $0.00039 | $0.00375 |
| Opus 5 | $0.00019 | $0.00187 |
| Sonnet 5 | $0.00008 | $0.00075 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
ship scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
6. **Smoke**: every URL in recipe `smoke` answers 200 — `curl -s -o /dev/null -w "%{http_code}" <url>`. What it actually says
op:ship
The release ritual. Steps run in order; a failing step stops the pipeline and reports.
- Preflight:
git status— summarize what ships. Run the recipetestcommand when present; failures stop here. - Commit: follow the repo's own style (
git log --oneline -5first). Stage files by name. - Push: gated (confirm) unless co-pilot armed; to an existing upstream only.
- Deploy: recipe
deploy— always confirm, armed or not (production). Missing key → op:project-recipes discovery; never guess a target. - Live verify (the blocking step): set
BUSTto the current epoch seconds; run recipecache_checkwith$URLand$BUSTsubstituted, or fetchlive_url?v=$BUSTand look for a marker from the just-shipped change (new text, version string, asset hash). Stale → report loudly, offer reciperollbackwhen present, and do not use the word "shipped". - Smoke: every URL in recipe
smokeanswers 200 —curl -s -o /dev/null -w "%{http_code}" <url>. - Screenshot the live page at a desktop width: Playwright MCP when available, else
npx playwright screenshot --viewport-size=1440,900 "$URL" <scratchpad>/ship-<date>.png.
Proof at end: live URL, screenshot path, status line.
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.
- 2d ago First seen · 19 lines · 39 tokens per session scan A b69d5c4bbac6
ship is a skill published in the GitHub repository artttj/rapid-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 375 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
land-and-deploy
Land and deploy workflow. (gstack).
release-plannotator
Prepare and execute a Plannotator release — draft release notes with full contributor credit, bump versions across all package files, build in dependency order, and kick off the tag-driven release pipeline. Use this skill whenever the user mentions preparing a release, bumping versions, writing release notes, tagging…
release
Release workflow for deploying OpenEnv environments to Hugging Face Spaces and keeping canonical references in sync.
publish
Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only: never runs pre-publish-review or re-reviews merged code unless the user explicitly asks. Argument: . Triggers: publish, release, deploy, npm publish.
pre-publish-review
Nuclear-grade 16-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (5 agents) for holistic review, and 1 oracle for overall release synthesis. Runs ONLY when the user…
work-with-pr
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the…