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.
git 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/commands/untrivial-ai/agent-orchestrator/spawn)<a href="https://agentmods.dev/commands/untrivial-ai/agent-orchestrator/spawn"><img src="https://agentmods.dev/badge/commands/untrivial-ai/agent-orchestrator/spawn/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/commands/untrivial-ai/agent-orchestrator/spawn"><img src="https://agentmods.dev/badge/commands/untrivial-ai/agent-orchestrator/spawn.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 | $0.00000 | $0.00845 |
| Opus 5.5 | $0.00000 | $0.00338 |
| Sonnet 5.5 | $0.00000 | $0.00169 |
| Haiku 4.5 | $0.00000 | $0.00085 |
Grade A, and why
spawn 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 16d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- spawn — 95% identical, 41 lines differ
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ao spawn
Spawn a worker or orchestrator agent session in a registered project, or a standalone worker session that is not tied to a project.
Standalone sessions run in an AO-managed directory. Register a project first with ao project add for project-scoped sessions.
Syntax
ao spawn [flags]
Flags
| Flag | Meaning | Default / Required |
|---|---|---|
--branch string |
Branch for the session worktree | ao/<session-id>/root |
--claim-pr string |
Immediately claim an existing PR for the spawned session | - |
--kind string |
Session role: worker or orchestrator |
worker |
--harness string |
Agent harness to use (see list below) | Project worker.agent; required if the project has none |
--issue string |
Issue id to associate with the session | - |
--model string |
Agent model override for this session only; overrides project/role config | - |
--name string |
Display name shown in the sidebar (max 100 characters) | Required |
--mode chat|tui |
Initial session interface; Chat requires harness support | Daemon default, otherwise Terminal UI |
--no-takeover |
Refuse if another active session owns the claimed PR (requires --claim-pr) |
- |
--project string |
Project id to spawn the session in | Optional when --standalone is used; defaults to AO_PROJECT_ID or the current repo's registered project |
--standalone |
Spawn a projectless worker session in an AO-managed directory | Disabled when --project is set |
--prompt string |
Initial prompt for the agent | - |
--skip-agent-check |
Skip CLI readiness warnings; the daemon still validates launch readiness | - |
--tracker-provider string |
Issue tracker provider: github or gitlab |
github |
--agent is an alias for --harness.
Available harnesses: claude-code, codex, aider, opencode, opencode-v2, grok, droid, amp, agy, crush, cursor, qwen, gemini, copilot, goose, auggie, continue, devin, cline, kimi, muse, kiro, kilocode, vibe, pi, kimchi, prime-agent, autohand, omp, fx, unreal-agent, mimo-code, deepseek-harness. Check ao agent ls --refresh for readiness on the installed build. unreal-agent is Chat-only; Gemini and MiMo Code are Terminal UI-only.
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.
- 16d ago Changed · +17 lines dd298d049aad
- 20d ago Changed 3556dd44bba4
- 21d ago Changed 971a5b23354d
- 22d ago Changed · +2 lines ebc446b01a06
- 29d ago Changed 68de46d936ba
- 1mo ago Changed · +2 lines e9aa9e05877b
- 1mo ago First seen · 39 lines · 0 tokens per session scan A e0fc1f4e3e60
spawn is a command published in the GitHub repository Untrivial-ai/agent-orchestrator (13,307 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 845 tokens. 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 commands, from other repositories
sync-status
Preview what would be synced between AI coding assistants without making changes.
commit-push-pr
Commit, push, and open a PR.
commit
Run when user calls /commit or asks to generate a commit message. Analyzes staged changes and writes a structured commit message.
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
update-vst-ui
Build the VST UI and deploy the static files into the vios tree (services/vios of the video-search-and-summarization repo), both ingress/vst-ui and webroot, then commit.
sync-to-copilot
Sync skills and instructions from Claude or Codex to GitHub Copilot CLI.