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/model-ids.md

View on GitHub
# Model Selection

Use `-m <id>` to request a model and `--spec-model <id>` to choose a planning model for specification mode.

```sh
droid exec -m claude-opus-4-8 "Review this authentication design."
droid exec --use-spec --spec-model claude-opus-4-8 --auto medium "Plan and implement the migration."
```

## Do Not Hard-Code a Catalog

Factory's model catalog is account- and release-dependent. Model IDs, defaults, reasoning levels, and BYOK availability change more quickly than this skill should. Discover the available values in the installed CLI:

```sh
droid exec --help
```

Then choose the smallest adequate option for the task. Pin an ID in a repository workflow only when reproducibility is more valuable than automatic upgrades, and document why it is pinned.

## Mission Roles

Mission mode can select worker and validator models separately. Choose a faster worker only when the mission specification and validation checks are strong enough to detect implementation mistakes.
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