The six backend jobs and the access table (free sample)
by PaperChaseWebb
The six jobs every backend does, a default-deny access table, two rules to paste into your agent's rules file and a prompt that tests access as three people.
- Price
- Free
- Difficulty
- Beginner
- Setup
- 15 min
- Format
- .md file
six-backend-jobs-and-access-table-free-sample.md · 2 KB · direct download, no signup
What you end up with
You know what your agent is really building when it adds a backend, and you can test who can read what.
What you get
- The six backend jobs
- The access table
- Two rules
- A check prompt
Who it is for
Anyone whose agent just added a database and who wants to know who can read it.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: Plain Markdown, so it also pastes into other agents such as Grok Bot, Hermes, OpenClaw or Muse. We list those as compatible by format only, not as tested.
Tools needed
Cost to run: Free.
Time to result: Fifteen minutes
Sample prompts, free to use
Here is the access table [paste]. Write a test script that tries to read and change one record in each table as owner, other user and signed out, and prints pass or fail per cell. Do not change any rules. Show me the output.
One wrong cell is a stop.
Free preview of the file
# The six backend jobs and the access table (free sample) A free sample from Backends for Agent-Built Apps by PaperChaseWebb. Works with Claude Code, Codex, Cursor or any coding agent. When you ask an agent to "add a backend", you are asking for six jobs. Name them, or it will build the two it finds interesting. ## The six jobs | Job | Plain question it answers | What breaks when it is missing | |---|---|---| | Store | Where does the data live, and does it survive a restart? | Data vanishes, or lives only in one browser | | Identify | Who is this person? | Anyone can claim to be anyone | | Allow | What is this person allowed to read and change? | One user reads another user's records | | Hold secrets | Where do the keys to paid services live? | A key leaks and someone else spends on it | | React | What happens when an outside service calls in? | Charges with no order, or one order per retry | | Run later | What runs on a schedule or after the request ends? | Emails never go out, reports never get built |
Worth knowing
- Access rule syntax differs by service. Check your service's current docs.
Questions
What is in the full guide?
Five backend shapes and a six-question picker, a BACKEND.md contract, safe migrations, secrets, idempotent webhooks and jobs, a free tier honesty sheet, live monitoring with a human gate, a rules block and 14 prompts.
Details
Version 1.0 · Updated Oct 27, 2026 · Markdown version of this page
License: Personal and commercial use. Download terms
Related

Backends for Agent-Built Apps: pick a shape, write the contract, keep the data safe
A teaching guide for the server side of apps your coding agent builds. Pick one of five backend shapes with six questions, write a BACKEND.md contract the agent follows, and get migrations, sign-in, access rules, secrets, webhooks, jobs, free tier limits and live monitoring right. Includes a rules block and 14 prompts.

Pre-launch security prompts for vibe-coded apps: Supabase RLS, leaked keys and open doors
14 prompts that make your coding agent find exposed keys, tables without row level security, open buckets and unverified webhooks in your own app, then fix them one commit at a time.

Spec-First Build Docs: PRD, design system, architecture note, agents guide and readiness check
A Markdown pack of the four documents to write before an agent builds anything, sized to the stakes: a PRD an agent can build from without inventing scope, the smallest design system that holds, a one-page architecture note with reversal costs, an agents guide with a project tree for Claude Code, Codex and Cursor, a weekly staleness pass and a nine-area readiness check.