Understand the repository first, then deliver one end-to-end feature with the smallest justified change surface.
Task specification
Task type
Feature iteration
Target platform
Web
Existing project
Required
Compatible tools
Codex · Claude Code · Cursor · GitHub Copilot
Optional context
Add context when it helps
This prompt works as-is. Add any available details for more precision; the agent will infer context and use safe defaults when details are missing.
An accessible project and run instructions
The complete feature request and user journey
Interfaces or behavior that must remain compatible
Observable acceptance criteria and permission boundaries
Ready-to-use prompt
Complete coding prompt
Copy and run it as-is. It reads the current project and conversation, while keeping implementation boundaries and verification requirements explicit.
Act as a coding agent working inside an existing repository. Implement the current feature request in the current accessible project, cover the current user journey, preserve the current compatibility requirements, and satisfy the current acceptance criteria. First read the relevant code, tests, configuration, dependencies, and project guidance. Inspect the Git working tree and preserve every unrelated change. Do not ask questions that the repository can answer, and do not assume a backend, permission, or data contract exists.
Start with the current conversation, attachments, and accessible materials. Treat available information as the input. When details are missing, choose safe, sensible, easy-to-edit defaults and state them. Ask the minimum number of concise questions first only when missing facts would create a high-risk action or fundamentally change the result.
Restate the goal and non-goals, then list concrete, falsifiable assumptions. Ask at most three blocking questions only when a wrong answer would invalidate the approach, and include a recommended default. Continue the remaining work with the safest choice that matches existing conventions. Trace the real user journey through entry points, state, data boundaries, and failure paths. Reuse existing components and services. Change only files required for the outcome. Cover loading, empty, error, retry, insufficient-permission, and duplicate-action states; consider idempotency, concurrency, and rollback for writes. Do not opportunistically refactor unrelated modules, upgrade dependencies, or change public contracts.
Add tests for important branches in the repository's style, run the real application through the journey, and execute formatting, type, test, and build checks. If an assumption proves false, pause the affected work and explain the evidence and smallest adjustment instead of silently expanding scope. Report the visible result, changed files, data or API impact, actual command and page evidence, uncovered branches, and rollback path. Claim completion only when both end-to-end behavior and repository gates truly pass.
After it finishes
Do not rely on a claim of completion
Check the real page, runtime behavior, and test evidence item by item.
Unrelated working-tree changes remain intact
Happy and failure journeys are verifiable
Critical tests and repository gates pass
API impact remaining risks and rollback are explicit
Inspiration source
This prompt is an original adaptation. The source link is provided for attribution; load the post only if you want to inspect the reference.
The X embed stays off until you choose to load it. Loading it may share your IP address and browser information with X.