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/rules/kensaurus/cursor-kenji/full-stack-ship-discipline)<a href="https://agentmods.dev/rules/kensaurus/cursor-kenji/full-stack-ship-discipline"><img src="https://agentmods.dev/badge/rules/kensaurus/cursor-kenji/full-stack-ship-discipline/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/rules/kensaurus/cursor-kenji/full-stack-ship-discipline"><img src="https://agentmods.dev/badge/rules/kensaurus/cursor-kenji/full-stack-ship-discipline.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 | $0.00558 |
| Opus 5.5 | $0.00021 | $0.00223 |
| Sonnet 5.5 | $0.00011 | $0.00112 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
full-stack-ship-discipline 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 27d 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
Full-Stack Ship Discipline
A feature is not done when the UI compiles — it is done when the flow works end-to-end against the remote backend the user actually hits. The recurring failure this prevents: a migration file authored beside a feature is never deployed, the live API 404s, and the bug masquerades as a UI issue.
- Inventory backend dependencies first. Before editing components ask: does this read/write data, call an RPC, or depend on a table / column / function / policy / bucket / secret? Fix those in the same turn.
- Deploy schema, don't just author it. Supabase:
apply_migration/execute_sqlon the confirmedproject_id, then verify in the same turn — re-queryinformation_schema/pg_proc/pg_policies, exercise the surface asanon/authenticated, checkquery_logsandget_advisors. Other stacks: run the real deploy command (prisma migrate deploy,drizzle-kit push,rails db:migrate, …) against the confirmed environment before the turn ends. - Keep file and deploy in sync. SQL applied via MCP also gets a matching
versioned file in the repo's migrations folder. Do not
git pushunless the user asked in this turn. - Edge functions, secrets, RLS, buckets, and cron jobs count as schema —
deploy and configure them with the UI change (
verify_jwt, CORS, keys). - Schema vs data. Deploy schema the user asked to ship without
re-asking — the request was the approval. Ask before mutating production
data (
DELETE/TRUNCATE/UPDATEon real rows) — it is hard to reverse. - Do not attach during a present-then-stop pass. If the active skill is
plan-*or a read-onlyaudit-*, emit findings/plan only — do notapply_migrationor deploy until the user approves a phase.
Done means: remote objects verified to exist, anon + authenticated paths exercised, migration file on disk, and the frontend observed hitting a 200 — not a stale 404.
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.
- 27d ago Changed de759560273f
- 1mo ago First seen · 38 lines · 53 tokens per session scan A 4827fa758b34
full-stack-ship-discipline is a cursor rule published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 22d ago), licensed MIT. It adds 53 tokens to every session and 558 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 2026-09-03.
Other cursor rules, from other repositories
composer-fullstack-delivery
New screen, feature, endpoint, or multi-layer slice — freeze seams, ship one demoable path, failure modes, Run/Wired handoff. Skip for a single-module code change.
prisma
Prisma: schema modeling, queries, migrations.
supabase
Supabase: RLS, edge functions, realtime.
convex
Convex: real-time backend, queries, mutations, schema.
sequelize
Sequelize: ORM models, migrations, associations.
sqlalchemy
SQLAlchemy: sessions, models, relationships, async.