Resources

Master prompts

Build a small working web application — master prompt

Deliver one complete user journey with honest state handling and useful verification.

CodexClaude CodeCursor
Pristren originalFree1.0.0 · original authored template; documentation reviewed 2026-11-17

A small application that completes one defined task, with validation, persistence choices, and a repeatable check.

Use this prompt after supplying a concrete project or task and the constraints that determine success. Select your AI tool in the workflow for host-specific setup. Review the prerequisites and choose only relevant resources; the prompt does not automatically include an entire directory.

Choose one vertical slice and implement input, processing, result, and failure states before adding secondary features.

After execution, check the workflow’s acceptance criteria against observed behavior. Treat illustrative examples as examples, and record anything not actually verified. Project details stay in your browser when you tailor this template.

Make the prompt yours.

Master prompt

Complete project or task to copy your tailored prompt.

Build a small working web application for [Describe the project, audience, and useful result.] under Use existing project conventions. State assumptions and verify the result..

Inspect the repository and existing conventions. Restate the target user and one end-to-end job. Define the inputs, expected output, persistence requirement, and acceptance examples. Propose the smallest implementation that completes that job. Surface any missing requirement that affects data ownership, authentication, or external costs before choosing a service.

Implement a complete vertical slice: an understandable entry screen, validated inputs, the core operation, a useful result, and recoverable empty/loading/error states. Validate untrusted data at the server boundary where a server exists. Keep credentials out of client code. Avoid adding speculative dashboards, account systems, or dependencies unrelated to the agreed task.

Use existing scripts and create a focused behavior check for the important journey. Verify one normal input, one invalid input, refresh/persistence behavior, and a recoverable failure. Explain what is real, what is mocked, and what requires configuration. Return the commands actually run, their results, and any remaining release requirements.

Execution environment: Codex. Follow applicable project instructions and verify the requested result.

Use it with your tool.

Documentation reviewedChecked 2026-11-17

Tool setup checked against official documentation. Pristren has not executed this workflow through this tool.

  1. Start Codex in the repository and read applicable AGENTS.md guidance. Include only the files this task needs.
  2. Choose one vertical slice and implement input, processing, result, and failure states before adding secondary features.
  3. Use the acceptance checks below to assess the result; an agent completion message is not evidence that the task passed.
Official setup documentation

License and access: MIT for this Pristren-authored prompt or instruction text.

Part of a bigger picture.

Sources and review notes