Agent Orchestrator is a local desktop workspace for running and supervising multiple coding agents, giving each task its own session, workspace, branch, and feedback loop. It is for developers coordinating agent fleets across repositories, pull requests, CI runs, reviews, and merges. The catalogue entries are commands, skills, and instructions for working with this orchestrator.
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 Untrivial-ai/agent-orchestrator --skill using-aogit clone --depth 1 https://github.com/Untrivial-ai/agent-orchestratorWrote 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/untrivial-ai/agent-orchestrator/using-ao)<a href="https://agentmods.dev/skills/untrivial-ai/agent-orchestrator/using-ao"><img src="https://agentmods.dev/badge/skills/untrivial-ai/agent-orchestrator/using-ao/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/untrivial-ai/agent-orchestrator/using-ao"><img src="https://agentmods.dev/badge/skills/untrivial-ai/agent-orchestrator/using-ao.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 | $0.00071 | $0.01161 |
| Opus 5.5 | $0.00028 | $0.00464 |
| Sonnet 5.5 | $0.00014 | $0.00232 |
| Haiku 4.5 | $0.00007 | $0.00116 |
Grade A, and why
using-ao 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 11d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AO CLI Catalog
ao is a thin CLI over the local AO daemon. Every command is ao <command> --help for the authoritative flag list.
| Command | What it does | When to use | Details |
|---|---|---|---|
spawn |
Spawn a project worker, orchestrator, or projectless standalone worker | Starting a new task or issue | commands/spawn.md |
session |
Manage agent sessions (list, kill, rename, restore, etc.) | Inspecting or controlling running/terminated sessions | commands/session.md |
agent |
Inspect installed harnesses and launch readiness | Choosing or diagnosing an agent harness | ao agent ls --refresh |
pr |
Merge a PR or resolve its review threads | Completing a reviewed change | ao pr merge / ao pr resolve-comments |
project |
Register, inspect, configure, or remove projects | Setting up or managing repos AO knows about | commands/project.md |
automation |
Manage durable recurring session automations | Creating, editing, disabling, deleting, and inspecting scheduled runs | commands/automation.md |
cue |
Create or list reusable project Cues | Saving a repetitive command or agent task at the user's request | commands/cue.md |
orchestrator |
List orchestrator sessions | Viewing which sessions are orchestrators | commands/orchestrator.md |
review |
List, submit, cancel, or trigger a reviewer pass for a worker's PR | Managing a code review loop | commands/review.md |
send |
Send a message to a running agent session | Correcting or directing a live agent | commands/send.md |
report |
Persist a meaningful worker report | Checkpoints, blockers, decisions, outputs, and completion | commands/report.md |
preview |
Start a session-owned app or open an exact URL/file | Running and showing the worker's relevant app, Markdown, HTML, PDF, or image | commands/preview.md |
browser |
Inspect and control the session's shared live browser | Verifying a web app through snapshots, interactions, waits, screenshots, console, and errors | commands/browser.md |
start |
Fetch (if needed) and open the AO desktop app | Launching the app | commands/start.md |
stop |
Stop the AO daemon | Shutting down AO | commands/stop.md |
status |
Show daemon status | Verifying the daemon is up and healthy | commands/status.md |
doctor |
Run local health checks | Diagnosing AO setup problems | commands/doctor.md |
import |
Import projects from a legacy AO install | Migrating from the old flat-file store | commands/import.md |
version |
Print version information | Checking installed version | - |
completion |
Generate shell completion scripts | Setting up tab completion | - |
What ships with it
17 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.
- commands/automation.md 2.9 KB
- commands/browser.md 12 KB
- commands/cue.md 1.6 KB
- commands/doctor.md 400 B
- commands/import.md 1017 B
- commands/orchestrator.md 506 B
- commands/preview.md 5.2 KB
- commands/project.md 6.4 KB
- commands/report.md 1.6 KB
- commands/review.md 2.6 KB
- commands/send.md 2.3 KB
- commands/session.md 6.5 KB
- commands/spawn.md 3.1 KB
- commands/start.md 531 B
- commands/status.md 400 B
- commands/stop.md 366 B
- references.md 3.4 KB
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.
- 11d ago Changed · +2 lines c8b02badbcda
- 14d ago Changed · +4 lines c511e18be075
- 15d ago Changed · +2 lines · +9 tokens per session b7bfd984c828
- 18d ago Changed · +1 lines 17dc465647b3
- 22d ago Changed · +1 lines 51cb0e436810
- 1mo ago Changed ac2a58b5161b
- 1mo ago First seen · 45 lines · 62 tokens per session scan A 3aa01b1ecb5f
using-ao is a skill published in the GitHub repository Untrivial-ai/agent-orchestrator (13,060 stars, last pushed 5d ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,161 once invoked, about $0.0003 per session on Opus 5.5. 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
knowledge-harvest
Source-backed project knowledge maintenance. Load only after the user explicitly activates cortex:orchestrator with harvest or harvest-refresh; never infer this route from repository state.
orchestrator
Explicit Cortex coordination for user outcomes, continuous incident ownership and evidence-based completion. For the initial skill read, emit the complete result object with text(result), preserving output and exitcode or a running sessionid.
worker-senior-consultant
Cortex delegated specialist only: Bounded senior consultant for coordinator-requested decisions using selected published reports only.
context-compaction
Restore coordinator and specialist context after compaction or restart. For the initial skill read, emit the complete command result with text(result), preserving output and exitcode or a running sessionid.
documentation-sync
Update affected project knowledge after verified changes while preserving manual documentation.
tool-discipline
Prevent guessed, incomplete and replayed tool calls during explicitly selected Cortex coordinator or worker work.