gan-build
Run a generator/evaluator build loop for implementation tasks with bounded iterations and scoring.
- Kind
- Prompt
- Works with
- Claude Code, Codex
- Source
- affaan-m/ECC @ d3b8a3e90890
- Path
- commands/gan-build.md
- License
- MIT
- Jobs
- Implementation, Review, Automation
InstallCopy it from the source repository, or sign in and let the assistant adapt it for your project.
Parse the following from $ARGUMENTS:
1. `brief` — the user's one-line description of what to build
2. `--max-iterations N` — (optional, default 15) maximum generator-evaluator cycles
3. `--pass-threshold N` — (optional, default 7.0) weighted score to pass
4. `--skip-planner` — (optional) skip planner, assume spec.md already exists
5. `--eval-mode MODE` — (optional, default "playwright") one of: playwright, screenshot, code-only
## GAN-Style Harness Build
This command orchestrates a three-agent build loop inspired by Anthropic's March 2026 harness design paper.
### Phase 0: Setup
1. Create `gan-harness/` directory in project root
2. Create subdirectories: `gan-harness/feedback/`, `gan-harness/screenshots/`
3. Initialize git if not already initialized
4. Log start time and configuration
### Phase 1: Planning (Planner Agent)
Unless `--skip-planner` is set:
1. Launch the `gan-planner` agent via Task tool with the user's brief
2. Wait for it to produce `gan-harness/spec.md` and `gan-harness/eval-rubric.md`
3. Display the spec summary to the user
4. Proceed to Phase 2
### Phase 2: Generator-Evaluator Loop
```
iteration = 1
while iteration <= max_iterations:
# GENERATE
…