Skip to content

BumpyClock/agent-templates / skills_archive/subagent-driven-development

subagent-driven-development

Unverified

Use 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.

references/parallelization-examples.md

View on GitHub
# Parallelization Examples (Optional)

Use when task feels splittable but boundaries fuzzy.

## Split by Layer

- Lock controller/service/repo boundaries first.
- Give each agent one layer.
- Keep one agent on integration tests.
- Use `developer` for shared boundary changes; use `developer-lite` only after interfaces are stable.

## Split by Surface

- UI components
- State/data layer
- API/client layer
- Tests per surface

Works only if props, API shapes, and ownership are explicit.

## Split by Failure Cluster

- One agent per bug/root cause.
- One agent for regression tests if shared files stay minimal.
- One integrator to merge and rerun checks.

## Do Not Split

- Same file set.
- Same public interface still in flux.
- High-churn refactors where each task will collide.
- Unclear ownership or tests that require the same fixtures to be rewritten by multiple agents.
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: 464kUpdated Claude CodeCodexVerifiedInstall
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: 464kUpdated Claude CodeCodexVerifiedInstall
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: 318kUpdated Claude CodeCodexUnverifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 318kUpdated Claude CodeCodexUnverifiedInstall