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/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/ship-and-observe)<a href="https://agentmods.dev/commands/kensaurus/cursor-kenji/ship-and-observe"><img src="https://agentmods.dev/badge/commands/kensaurus/cursor-kenji/ship-and-observe.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.00393 |
| Opus 5 | $0.00015 | $0.00197 |
| Sonnet 5 | $0.00006 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
ship-and-observe 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 8d 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 & Observe
Take merged, repository-green code all the way to a verified, monitored
production release for a running app. For npm package releases use
/deploy-npm instead.
Follow the workflow-ship-and-observe skill end to end. In brief:
- Pin the target and revision — confirm the exact merged SHA and the
environment/provider (discover from
vercel.json,fly.toml,Dockerfile, CI deploy workflows, EAS, Terraform, etc.). Identify the deploy mechanism, backend dependencies, an executable rollback plan, and the signals + thresholds that mean "roll back". - Preflight — repo green, revision merged; deploy and verify backend dependencies first (migrations, functions, RLS, secrets).
- Deploy via the real pipeline and wait for a terminal state.
- Verify the revision is live — the deployed build must equal the intended SHA (deployment metadata / version endpoint / asset hash), not just a 200. Smoke-test critical flows against production with evidence.
- Observe the defined stability window; crossing a threshold triggers rollback or hotfix.
- Report STABLE / ROLLED BACK / HOTFIXED / BLOCKED with evidence.
Shipping is not merging. Deployed-verified needs a proven live revision; observed-stable needs the monitoring window to pass.
The full playbook lives in the workflow-ship-and-observe skill.
Related: deploy-verify, full-stack-ship-discipline, iterate-post-launch,
workflow-feedback-to-closure.
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.
- 8d ago First seen · 36 lines · 31 tokens per session scan A be58b3c1f398
ship-and-observe is a command published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 10d ago), licensed MIT. It adds 31 tokens to every session and 393 once invoked, about $0.0002 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 commands, from other repositories
publish
Publish oh-my-opencode to npm via GitHub Actions workflow.
get-unpublished-changes
Compare HEAD with the latest published npm versions and list all unpublished changes by release layer.
ship
Seen on their staging, then live. Rollback you have run.
release-notes
Write user-facing release notes from a changelog or list of changes, grouped and written for the reader.
changelog-from-diff
Turn a diff or commit list into user-facing changelog entries that describe outcomes, not code.
release-announcement
Announce a release so users know what changed, what breaks, and what to do about it.