BumpyClock/agent-templates / skills_archive/subagent-driven-development
subagent-driven-development
UnverifiedUse when executing a defined implementation plan with multiple mostly-independent tasks in the current session. Orchestrate implementer and reviewer subagents, parallelize safe work, keep architecture and integration in the orchestrator.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.4 KB |
| agents/openai.yaml | config | 225 B |
| references/example-workflow.md | markdown | 1.1 KB |
| references/guardrails.md | markdown | 1.3 KB |
| references/parallelization-examples.md | markdown | 881 B |
references/example-workflow.md
View on GitHub# Example Workflow
Short loop example.
```
1. Read plan once. Split into small owned tasks.
2. Define shared interfaces first.
3. Create `tsq` items. Mark ready vs blocked.
4. Pick implementer: `developer-lite` for clear local task, `developer` for judgment task.
5. Dispatch implementer with full task text, owned files, contracts, tests.
6. Implementer asks one question. Orchestrator answers and updates prompt.
7. Implementer returns status, summary, changed files, tests run, self-review, open issues.
8. If status is `NEEDS_CONTEXT`, `BLOCKED`, or correctness-related `DONE_WITH_CONCERNS`, provide context, split, or upgrade agent.
9. Dispatch `reviewer` with `Review mode: spec-compliance`.
10. Reviewer fails task for one missing acceptance criterion.
11. Send targeted fix task back to implementer.
12. Spec reviewer passes.
13. Dispatch `reviewer` with `Review mode: code-quality`.
14. Quality reviewer passes.
15. Mark task done in `tsq`.
16. Integrate approved tasks in dependency order.
17. Run final checks across the full plan.
18. Dispatch `reviewer` with `Review mode: final-integration`.
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 464k | Updated | Claude CodeCodex | Verified | Install |
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 464k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 318k | Updated | Claude CodeCodex | Unverified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 318k | Updated | Claude CodeCodex | Unverified | Install |