Skip to content

magnus919/hermes-droid / factory-droid

factory-droid

Verified

Use 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.

references/mission-mode.md

View on GitHub
# Mission Mode

Mission mode turns a clear multi-step goal into an orchestrated session with worker and validation roles.

## Use It When

- The task spans several files or modules.
- The desired outcome and validation criteria are explicit.
- Parallel work or independent validation materially reduces risk.

Do not use it for a single-file fix, exploratory work that needs frequent steering, or a task without a credible success condition.

## Mission File

Put the outcome, boundaries, and checks in a file:

```markdown
# Goal
Replace session authentication with JWT authentication.

## Scope
- src/auth/
- affected route handlers
- auth tests

## Constraints
- Maintain backward compatibility for current sessions.
- Do not add dependencies without documenting why.

## Validation
- Focused auth tests pass.
- Existing session migration behavior is covered.
```

Then run it in a named worktree with the required high autonomy:

```sh
droid exec --mission --auto high --worktree auth-jwt -f mission.md
```

Mission mode auto-approves proposals. Treat it as a higher-impact operation: review the mission file, inspect the resulting worktree, and run the project checks yourself before merging.

## Model Tuning

`--worker-model`, `--worker-reasoning-effort`, `--validator-model`, and `--validator-reasoning-effort` tune roles when Factory makes those models available. Discover supported values with `droid exec --help` before pinning them in automation.
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: 472kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall