Wukong Code

Make coding agents work like engineers

A software development methodology for coding agents.

From discovery and design through TDD, code review, and final verification, AI does more than generate code—it completes reliable software engineering work.

26 top-level skills · 10 development environments · zero core dependencies · MIT licensed

  1. Clarify goals, boundaries, and acceptance criteria

  2. Compare approaches and obtain approval

  3. Break down tasks, risks, and verification commands

  4. RED → GREEN → REFACTOR

    • RED
    • GREEN
    • REFACTOR
  5. Check requirement fit and code quality

    evidence attached
  6. Run fresh tests, builds, and reproductions

    PASS
  7. You choose the final integration path

A failed check returns work to the stage that needs evidence

The problem

AI writes fast. Reliable delivery is another matter.

  1. The code is generated before the requirement is clear.

  2. The bug is not located, so every change is a guess.

  3. The agent declares success before the tests run.

Wukong Code gives coding agents the missing engineering process, so every implementation is grounded in design, tests, and verification.

Core capabilities

Make reliable software engineering the default

  1. Design before coding

    Clarify the goal, compare approaches, and obtain approval before implementation.

  2. Real test-driven development

    Follow RED–GREEN–REFACTOR: observe the failure, then write the smallest implementation.

  3. Systematic debugging

    Reproduce the issue, gather evidence, and trace the root cause before proposing a fix.

  4. Review throughout

    Continuously check requirement fit and code quality before drift becomes rework.

  5. Verify before declaring done

    Without fresh test, build, or reproduction results, a judgment is not a conclusion.

  6. Triggered by the task

    Skills select the right workflow from context without repeated magic phrases.

Delivery evidence

From idea to reliable delivery

Simple tasks stay simple. Complex tasks get the engineering constraints they need.

$ wukong run --task feature

  1. discovery ............. ✓
  2. design approval ....... ✓
  3. implementation plan ... ✓
  4. TDD (RED) ............. ✓
  5. TDD (GREEN) ........... ✓
  6. code review ........... ✓ evidence attached
  7. final verification .... ✓ PASS
  8. merge / PR ............ ready

Product design

Product Design belongs in the same workflow

Move from research, UX audits, and visual exploration to frontend implementation and Design QA.

  1. 01 · VISUAL EXPLORE Choose a direction
  2. 02 · BUILD Implement the real interface
  3. 03 · DESIGN QA Compare the rendered result
Visual target
Delivery workflow
Design → BuildDesign QA

Project dashboard

  • Requirements review To organize
  • Interaction states Unspecified
  • Design checks To review
Rendered result
Delivery workflow
Design → BuildDesign QA

Project dashboard

  • Requirements review Verified
  • Interaction states Covered
  • Design checks Passed

Method comparison

More than a prompt template

How ordinary prompts and Wukong Code approach software work
Dimension Ordinary prompt Wukong Code
Trigger Depends on manual reminders Triggers from the task
Scope Focuses on code generation Covers the delivery workflow
Debugging Relies on guesses Investigates the root cause first
Completion Depends on judgment Requires verification evidence

Environments

Use it in the environments you already know

Zero core dependencies. It does not install tools for your project or overwrite repository commands.

  1. Antigravity
  2. Claude Code
  3. Codex App
  4. Codex CLI
  5. Cursor
  6. Factory Droid
  7. GitHub Copilot CLI
  8. Kimi Code
  9. OpenCode
  10. Pi

Next step

Code can be generated quickly. Engineering quality cannot depend on luck.

Let agents do the right work at the right time, and keep your judgment at the key decision points.

Wukong Code helps AI produce more than code—it produces delivery you can trust.