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
-
Clarify goals, boundaries, and acceptance criteria
-
Compare approaches and obtain approval
-
Break down tasks, risks, and verification commands
-
RED → GREEN → REFACTOR
- RED
- GREEN
- REFACTOR
-
Check requirement fit and code quality
evidence attached -
Run fresh tests, builds, and reproductions
PASS -
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.
The code is generated before the requirement is clear.
The bug is not located, so every change is a guess.
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
-
Design before coding
Clarify the goal, compare approaches, and obtain approval before implementation.
-
Real test-driven development
Follow RED–GREEN–REFACTOR: observe the failure, then write the smallest implementation.
-
Systematic debugging
Reproduce the issue, gather evidence, and trace the root cause before proposing a fix.
-
Review throughout
Continuously check requirement fit and code quality before drift becomes rework.
-
Verify before declaring done
Without fresh test, build, or reproduction results, a judgment is not a conclusion.
-
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
discovery ............. ✓design approval ....... ✓implementation plan ... ✓TDD (RED) ............. ✓TDD (GREEN) ........... ✓code review ........... ✓ evidence attachedfinal verification .... ✓ PASSmerge / 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.
- 01 · VISUAL EXPLORE Choose a direction
- 02 · BUILD Implement the real interface
- 03 · DESIGN QA Compare the rendered result
Project dashboard
- Requirements review To organize
- Interaction states Unspecified
- Design checks To review
Project dashboard
- Requirements review Verified
- Interaction states Covered
- Design checks Passed
Method comparison
More than a prompt template
| 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.
- Antigravity
- Claude Code
- Codex App
- Codex CLI
- Cursor
- Factory Droid
- GitHub Copilot CLI
- Kimi Code
- OpenCode
- 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.