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/autonomy-levels.md

View on GitHub
# Autonomy Levels

Choose the lowest `droid exec` autonomy level that can complete the task. These permissions govern what the Droid session may do, not whether the task is safe or reviewed.

| Level | Allows | Use for |
|---|---|---|
| Default | Read-only inspection | Reviews, reconnaissance, plans |
| `--auto low` | Basic file operations in non-system directories | Documentation, formatting, narrow edits |
| `--auto medium` | Dependency installs, local Git operations, builds | Implementing and testing on a branch |
| `--auto high` | Pushes, deployments, sensitive or major side effects | Explicitly authorized delivery workflows |
| `--skip-permissions-unsafe` | All operations | Disposable, isolated environments only |

## Examples

```sh
# Understand before changing
droid exec "Trace all callers of src/auth/retry.py and propose the smallest root-cause fix."

# Make a narrow edit and test it
droid exec --auto medium "Fix the retry bug, run focused tests, and leave changes for review."

# Explicitly authorized remote side effect
droid exec --auto high "Run the documented release workflow and push only after tests pass."
```

## Hard Boundary

Never use `--skip-permissions-unsafe` in a working tree with valued data, production credentials, or unreviewed changes. It cannot be combined with `--auto` flags.

Verify current permission behavior with `droid exec --help`; the CLI's own help is authoritative.
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