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.
Factory Droid
Use Factory Droid through the droid CLI to delegate coding tasks. Prefer droid exec for bounded, non-interactive work; use interactive droid only when a user needs to steer the session.
Before You Delegate
- Confirm the task warrants an external coding agent. For a small, well-scoped edit, work directly.
- Work inside the target Git repository and set the command working directory explicitly.
- Verify installation and authentication before assigning a real task:
droid exec -o json --auto low "Respond with: OK" - Use the lowest autonomy level that completes the task. Never use
--skip-permissions-unsafeoutside a disposable sandbox.
For login and BYOK details, read references/authentication.md.
One-Shot Tasks
# Read-only analysis
droid exec "Map the authentication flow."
# Bounded implementation and local validation
droid exec --auto medium "Add retry logic to API calls, update focused tests, and report changed files."
# Parseable result for an orchestrator
droid exec -o json --auto low "List the public functions in src/auth.py."
Use a prompt file rather than shell quoting for complex instructions:
droid exec --auto medium -f .factory/task.md
Autonomy and Isolation
| Level | Use for | Avoid for |
|---|---|---|
| Default | Reconnaissance, reviews, plans | Any file change |
--auto low | Safe, bounded edits | Dependency installs or commits |
--auto medium | Implement, test, and make local commits | Push or deployment |
--auto high | Explicitly authorized push/deploy workflows | Routine development |
For the full decision matrix, read references/autonomy-levels.md.
Use a named worktree for non-trivial tasks so changes are reviewable and isolated:
droid exec --worktree fix-auth-retry --auto medium "Fix the auth retry bug, run focused tests, and leave changes uncommitted for review."
Specification-First Work
Use --use-spec for a change whose requirements or architecture are unclear enough that a plan reduces rework:
droid exec --use-spec --auto medium "Design and implement user profiles with avatar upload."
It costs more because Droid plans and implements. Do not choose it for a mechanical edit.
Mission Mode
Use mission mode only for a clear, multi-file objective that benefits from worker and validator roles:
droid exec --mission --auto high --worktree mission-auth-refactor -f mission.md
Read references/mission-mode.md before writing the mission specification. For model selection and provider-specific identifiers, read references/model-ids.md.
Output and Follow-Through
Request concrete outcomes: changed files, tests run and results, remaining risks, and a session ID when relevant. Inspect the working tree and run the project’s own checks before claiming completion. A Droid result is evidence, not proof.
For session continuation, reasoning effort, tool controls, explicit --cwd, and local session search, read references/advanced-operations.md.
Choosing an Agent
Read references/delegation-comparison.md when Factory Droid is one of several viable coding agents.
Pitfalls
droid execis non-interactive; do not allocate a TTY unless using the interactivedroidapplication.- Dirty worktrees may be preserved. Inspect the printed path before cleanup; never delete a worktree by guesswork.
- Use
-ffor prompts containing shell-sensitive text. - Treat model IDs, provider availability, and pricing as version-sensitive. Verify them rather than presenting examples as permanent facts.
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: 469k | 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: 321k | 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: 321k | 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: 321k | Updated | Claude CodeCodex | Verified | Install |