Borrowing it
Nothing to install: this file belongs to flisk-sh/flisk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/flisk-sh/flisk/main/.claude/skills/flisk-recipe-saas/SKILL.mdgit clone --depth 1 https://github.com/flisk-sh/fliskWrote 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/flisk-sh/flisk/flisk-recipe-saas)<a href="https://agentmods.dev/skills/flisk-sh/flisk/flisk-recipe-saas"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/flisk-recipe-saas/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/flisk-sh/flisk/flisk-recipe-saas"><img src="https://agentmods.dev/badge/skills/flisk-sh/flisk/flisk-recipe-saas.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 | $0.00082 | $0.00584 |
| Opus 5.5 | $0.00033 | $0.00234 |
| Sonnet 5.5 | $0.00016 | $0.00117 |
| Haiku 4.5 | $0.00008 | $0.00058 |
Grade A, and why
flisk-recipe-saas 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 5d 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.
Each answers 200: the `web` health URL, `/api/accounts/health`, `/api/accounts/health/db`, `/api/billing/health` and `/api/billing/health/db` on `api.<project>.localhost:<port>`. Also sign up and log in once with `curl` What it actually says
Recipe: a SaaS with login and billing
Parts: a web app, an accounts API (sign-up, login, sessions), and a billing API (plans and subscriptions). Both APIs store data in the stack's Postgres.
Steps
flisk doctor
flisk project --yes
flisk resource web --type frontend --stack saas --yes
flisk resource accounts-api --type backend --stack saas --feature drizzle --yes
flisk resource billing-api --type backend --stack saas --feature drizzle --yes
flisk up saas --dry-run
flisk up saas --json & # wait for {"ok":true}
flisk networks --stack saas --raw
App code
accounts-api:POST /signup,POST /login,GET /me. Hash passwords (Bun.password.hash). Sign session tokens withJWT_SECRET, which Flisk generates into the project.envand passes to the container. Do not invent a new secret file.billing-api:GET /plans,POST /subscribe,GET /subscription. Verify the caller's token with the sameJWT_SECRET.- Payments: without the user's test keys, record subscriptions in the database and say that no real payment provider is connected. If the user gives a provider's test key, list its name under
secrets.requiredinservices/saas/billing-api/service.jsonand put the value in the project.env, never in code. web: sign-up and login forms, a plans page, and a "your plan" page.
Done when
Each answers 200: the web health URL, /api/accounts/health, /api/accounts/health/db, /api/billing/health and /api/billing/health/db on api.<project>.localhost:<port>. Also sign up and log in once with curl and show the user it worked.
Then tell the user the web app URL, the two API URLs, that payments are not connected to a real provider (unless they are), and that flisk down stops everything.
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.
- 5d ago First seen · 40 lines · 82 tokens per session scan A c2e58b1bb2c8
flisk-recipe-saas is a skill published in the GitHub repository flisk-sh/flisk (54 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 584 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-15.
flisk-recipe-saas compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flisk-recipe-saasflisk-sh/flisk | Skill | 54 | yesterday | MIT | A | 82 | Claude Code |
| azure-postgres-tsmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 94 | Claude Code |
| supabasesupabase/agent-skills | Skill | 3.1k | 8d ago | MIT | A | 185 | Claude Code, Codex |
| butterbasebutterbase-ai/butterbase | Skill | 3.0k | yesterday | Apache-2.0 | A | 34 | Claude Code, Codex |
| supabase-clifcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 60 | Claude Code |
| firebase-data-connectfirebase/agent-skills | Skill | 519 | 11d ago | Apache-2.0 | A | 74 | Claude Code |
| database-patternsyonatangross/orchestkit | Skill | 305 | yesterday | MIT | A | 32 | Claude Code |