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 nikandr-surkov/ai-saas-starter --skill add-featuregit clone --depth 1 https://github.com/nikandr-surkov/ai-saas-starterWrote 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/nikandr-surkov/ai-saas-starter/add-feature)<a href="https://agentmods.dev/skills/nikandr-surkov/ai-saas-starter/add-feature"><img src="https://agentmods.dev/badge/skills/nikandr-surkov/ai-saas-starter/add-feature/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/nikandr-surkov/ai-saas-starter/add-feature"><img src="https://agentmods.dev/badge/skills/nikandr-surkov/ai-saas-starter/add-feature.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 | $0.00033 | $0.00534 |
| Opus 5.5 | $0.00013 | $0.00214 |
| Sonnet 5.5 | $0.00007 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
add-feature 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 2mo 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
Add a feature
Follow these steps in order. Look at an existing feature first —
src/app/(app)/generate/ is the reference implementation of this shape.
1. Spec it
Copy specs/TEMPLATE.md to specs/NNN-short-name.md and fill it in
(problem, solution, out-of-scope, data changes, test plan). Two paragraphs
beat zero. Show the user before writing code.
2. Data (only if the spec says so)
If the feature needs schema changes, stop and run /db-migration. Schema
changes require asking the user first.
3. Server action
Create src/app/(app)/<feature>/actions.ts:
"use server"at the top.- First line of every action: re-check the session via the helper in
src/lib/auth/— never rely on middleware alone. Throw/redirect if absent. - Validate all input with a Zod schema. Parse, don't cast.
- Mutations that touch credits go through
src/lib/credits/only. - Return typed results;
revalidatePathwhat the mutation changed.
4. Page
Create src/app/(app)/<feature>/page.tsx:
- Server Component. Fetch data directly (Drizzle), no client fetching.
- Re-check the session server-side, same as the action.
"use client"only for leaf components that need interactivity (forms, toggles) — keep them small, pass data down from the RSC.- UI per DESIGN.md: existing shadcn primitives from
src/components/ui/, ledger rows for lists, mono for numbers/labels, no new colors.
5. Navigation
Add the page to the sidebar nav in the app shell component (one entry: lucide icon + label).
6. Test
Write a Vitest file next to the logic you added (*.test.ts):
- Cover the action's happy path, invalid input (Zod rejection), and the unauthenticated case.
- If credits are involved, assert the ledger invariant still holds (balance cache === sum of transactions).
7. Done means done
pnpm typecheck && pnpm lint && pnpm test all green. Walk the feature once
in the browser (pnpm dev).
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.
- 2mo ago First seen · 62 lines · 33 tokens per session scan A a3847bb1fb4d
add-feature is a skill published in the GitHub repository nikandr-surkov/ai-saas-starter (28 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 534 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
better-t-stack
Create or extend an end-to-end type-safe TypeScript project with Better-T-Stack (create-better-t-stack). Use when the user wants to start, scaffold or bootstrap an app, API, fullstack project or monorepo with any of Next.js, TanStack Router or Start, React Router, Nuxt, Svelte, Solid, Astro, React Native, Hono…
cloudflare-platform-skill
Cloudflare platform development guidance — patterns, gotchas, decision trees, SDK usage for Workers, Pages, KV, D1, R2, AI, Durable Objects, and 60+ products. Use when building or developing ON the Cloudflare platform. For managing Cloudflare resources (DNS, WAF, DDoS, R2 buckets, Workers deployments), use the cf CLI…
heygen
Best practices for HeyGen - AI avatar video creation API.
designing-data-intensive-applications
Apply Martin Kleppmann-inspired data-system rules when designing reliability, scalability, consistency, replication, transactions, streams, or schema evolution.
implementing-domain-driven-design
Apply Vaughn Vernon-inspired implementation DDD rules when building aggregates, domain events, repositories, application services, or context integrations.
patterns-of-enterprise-application-architecture
Apply Martin Fowler-inspired enterprise architecture rules when choosing layers, service layers, transaction scripts, domain models, repositories, mappers, or DTOs.