agentleFS
Badhon-00Badhon-00/MDCP/skills/replica-backend/SKILL.md

replica-backend

Skill2 starsChanged 5 days agoMITView on GitHub

Builds the backend of an app clone: auth, database migrations and access rules, payments with Stripe, email, background jobs and third-party integrations through official APIs only, plus a security checklist. Use when the user says "add login", "set up auth", "wire up the database", "add payments", "connect Stripe", "add Google Calendar", "send emails", "backend for my clone", or when /replica-build is running on fake data.

  • Reads credentials

3 other projects use a version of this, 1 of them edited; 1 of 1 edited versions we compared changed its rules; 2 new projects in the last 4 weeks, against 0 the 4 before.

How people change it

1 of 1 edited versions changed its rules.

Of the 1 edited version we compared: 1 made changes of their own.

We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.

Adopted by

Surging: 2 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projectsWeek of Oct 25: 2 new projectsWeek of Nov 1: 0 new projectsWeek of Nov 8: 0 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 2 in all, so this is a hint, not a trend.

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Official, public APIs only, with the user's own keys: Never call the original app's private endpoints, never reuse its OAuth client, never …

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

replica-backend

Reads replica/architecture.md. Writes migrations and server code, and keeps replica/backend.md (checklist below) up to date.

The rules

  • Official, public APIs only, with the user's own keys. Never call the original app's private endpoints, never reuse its OAuth client, never proxy through it.
  • The user creates accounts and keys. Claude never signs up for services, never types a password, card or live key. The user creates the Stripe, Supabase, Resend or Google Cloud project and puts keys in .env.local. Claude writes .env.example with every variable name and no values.
  • Test mode first. Stripe test keys and test cards until replica-deploy.

Auth

  • Email sign up with verification, password reset, magic link if the original has it. OAuth (Google, Apple) with the user's own developer apps.
  • Sessions: http-only secure cookies. Sign out everywhere.
  • Roles and teams if the recon map has them: owner, admin, member, with one function that answers "can this user do this to this record".
  • Account deletion that actually deletes. Apple requires it for apps with sign up.

Database

  • Migrations from architecture.md, checked in, run by a script.
  • Access rules on every table: row level security policies on Supabase, or the authorisation function called in every query. Test it: a second user must get nothing back.
  • Seed script with realistic fake data (no real people).
  • Backups on (the host's daily backups count, check they are enabled).

Payments

  • Stripe Checkout for sign up to a plan, the Customer Portal for changes and cancelling. Do not build card forms.
  • Webhooks: verify the signature, store the event id, make every handler idempotent (Stripe retries). Handle checkout.session.completed, customer.subscription.updated, customer.subscription.deleted, invoice.payment_failed.
  • Subscription status lives in your database, updated by webhooks, read by your app. Never trust the client.
  • Cancelling is one click. Hard-to-cancel billing is a top complaint about most apps, and in many places it is illegal.

Email and jobs

  • Transactional email through Resend or Postmark from your own domain. Templates written fresh.
  • Jobs for anything time-based (reminders, digests, sync, cleanup) with retries and a dead-letter log. Times in UTC, shown in the user's zone.

Integrations

For each integration in the feature matrix: the official API, the OAuth scopes needed (fewest possible), the provider's review process, rate limits. Google scopes like Calendar need Google's OAuth verification before public launch, which takes weeks. Start it early and write that in backend.md.

Security checklist

  • secrets only in env vars, .env* in .gitignore, nothing in client bundles
  • input validated on the server (zod or similar) on every route
  • authorisation checked on every read and write, tested with a second user
  • rate limits on auth, sign up, and anything that sends email or SMS
  • webhooks verify signatures
  • uploads: size and type limits, served from a separate domain or bucket
  • no user data in URLs or logs
  • dependencies audited (npm audit)
  • privacy policy lists every processor (Stripe, Resend, host, analytics)

Output

Working auth, database, payments in test mode, email and the integrations, .env.example, replica/backend.md with the checklist ticked, feature matrix rows updated. Next: /replica-test.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.