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 AIOSAI/AIPass --skill drone_commandsgit clone --depth 1 https://github.com/AIOSAI/AIPassWrote 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/aiosai/aipass/drone_commands)<a href="https://agentmods.dev/skills/aiosai/aipass/drone_commands"><img src="https://agentmods.dev/badge/skills/aiosai/aipass/drone_commands/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/aiosai/aipass/drone_commands"><img src="https://agentmods.dev/badge/skills/aiosai/aipass/drone_commands.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00018 | $0.00490 |
| Opus 5 | $0.00009 | $0.00245 |
| Sonnet 5 | $0.00004 | $0.00098 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
drone_commands 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.
What it actually says
Drone Commands Skill
Execute drone commands programmatically. Drone is the AIPass CLI router that dispatches commands to system modules.
Available Actions
| Action | Description |
|---|---|
run |
Execute an arbitrary drone command string |
list |
List all available drone modules (drone systems) |
help |
Get help for a specific module (drone @module --help) |
Usage
drone @skills run drone_commands run --args '{"command": "drone @ai_mail inbox"}'
drone @skills run drone_commands list
drone @skills run drone_commands help --args '{"module": "ai_mail"}'
How Drone Routing Works
Drone uses @module syntax to route commands to the correct system module:
drone @ai_mail inbox -> routes to ai_mail module
drone @skills list -> routes to skills module
drone @devpulse dashboard -> routes to devpulse module
drone commons feed -> special case (no @ prefix)
drone systems -> lists all registered modules
Architecture
This skill follows the AIPass 3-layer pattern:
drone_commands/
SKILL.md # This file
handler.py # Top-level handler (delegates to apps/)
apps/
modules/
command_runner.py # Orchestrates drone command execution
handlers/
executor.py # Runs commands via subprocess
parser.py # Parses drone output
Output Format
All actions return structured dicts:
{"success": True, "output": "...", "error": None}
The run action returns the full stdout/stderr from the drone command.
Notes
- Commands execute in the AIPASS_ROOT directory by default
- Timeout defaults to 30 seconds (configurable)
- Never runs commands that modify system state without explicit action
- All output is captured, never printed directly
What ships with it
7 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 · 77 lines · 18 tokens per session scan A 3fdf7e2c8b56
drone_commands is a skill published in the GitHub repository AIOSAI/AIPass (274 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 490 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
ouroboros-run
Execute a Seed specification through the workflow engine.
seed
Generate validated Seed specifications from interview results.
auto
Automatically converge from goal to A-grade Seed and execute it.
evolve
Start or monitor an evolutionary development loop.
publish
Publish Seed specification as GitHub Issues for team-based project management.
qa
General-purpose QA verdict for any artifact type.