magnus919/hermes-droid / factory-droid
factory-droid
VerifiedUse this skill when delegating coding work to Factory Droid's droid CLI for code analysis, edits, specification-first implementation, worktree isolation, or multi-agent missions. Do not use it for small direct edits or when Factory Droid is unavailable.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.2 KB |
| references/advanced-operations.md | markdown | 2.2 KB |
| references/authentication.md | markdown | 939 B |
| references/autonomy-levels.md | markdown | 1.4 KB |
| references/delegation-comparison.md | markdown | 1.0 KB |
| references/mission-mode.md | markdown | 1.4 KB |
| references/model-ids.md | markdown | 990 B |
references/delegation-comparison.md
View on GitHub# Choosing a Coding Agent
Choose the tool based on the work, not brand preference.
| Need | Consider |
|---|---|
| Small edit with clear context | Work directly with the host agent's file and test tools |
| Non-interactive Factory task with JSON result | Factory Droid: `droid exec -o json` |
| Explicit specification-first planning | Factory Droid: `droid exec --use-spec` |
| Clear multi-step mission with worker and validator roles | Factory Droid: `droid exec --mission --auto high` |
| A different installed coding agent whose local workflow fits better | Consult that agent's own current documentation |
## Factory Droid Strengths
- Headless execution for automation
- Tiered autonomy controls
- Named Git worktree support
- Specification and mission modes
## Decision Rule
Do not select an agent from a static feature matrix. Check what is installed, authenticated, permitted, and appropriate for the repository. If the requested task is a small, bounded change, direct editing is usually lower-risk and cheaper than delegating it.
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: 472k | 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |