Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add magnus919/hermes-droid --skill factory-droidgit clone --depth 1 https://github.com/magnus919/hermes-droidWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/magnus919/hermes-droid/factory-droid)<a href="https://agentmods.dev/skills/magnus919/hermes-droid/factory-droid"><img src="https://agentmods.dev/badge/skills/magnus919/hermes-droid/factory-droid/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/magnus919/hermes-droid/factory-droid"><img src="https://agentmods.dev/badge/skills/magnus919/hermes-droid/factory-droid.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.00932 |
| Opus 5 | $0.00026 | $0.00466 |
| Sonnet 5 | $0.00011 | $0.00186 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
factory-droid scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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."
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 96 lines · 53 tokens per session scan A 0c7e8a4b5b94
factory-droid is a skill published in the GitHub repository magnus919/hermes-droid (6 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 932 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the…