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/cue)<a href="https://agentmods.dev/commands/untrivial-ai/agent-orchestrator/cue"><img src="https://agentmods.dev/badge/commands/untrivial-ai/agent-orchestrator/cue/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/cue"><img src="https://agentmods.dev/badge/commands/untrivial-ai/agent-orchestrator/cue.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 | $0.00364 |
| Opus 5.5 | $0.00000 | $0.00146 |
| Sonnet 5.5 | $0.00000 | $0.00073 |
| Haiku 4.5 | $0.00000 | $0.00036 |
Grade A, and why
cue 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 15d 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
ao cue
Create and inspect reusable Cues for a local AO project. Both orchestrators and workers can use this command from their sessions. The project defaults to AO_PROJECT_ID, then the current session's project, then the registered project containing the current directory. Pass --project <id> when the target differs.
When the user asks to turn a repetitive workflow into a Cue, first list the project's Cues to avoid creating a duplicate. Choose an agent Cue for a reusable natural-language instruction. Choose a command Cue only when the exact shell command is known. If the requested behavior is ambiguous, clarify the missing instruction or command before creating it. After creation, tell the user the Cue's name, kind, and what it will run.
ao cue list [--project <id>] [--json]
ao cue create --name <name> (--prompt <instruction> | --command <shell-command>) [--description <text>] [--project <id>] [--json]
--prompt creates an agent Cue. --command creates a command Cue. Supply exactly one. Use --json to inspect full definitions or the created Cue ID. The daemon validates length, project existence, and unique names; its API error code and request ID are preserved on failure.
Examples:
ao cue create --name "Review current PR" --prompt "Review the current PR for correctness and report actionable findings."
ao cue create --name "Run backend tests" --command "cd backend && go test ./..."
ao cue list --json
This CLI intentionally has no update or delete subcommands. If a matching Cue already exists, report it and ask the user to edit or delete it in project settings instead of replacing it.
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.
- 15d ago First seen · 23 lines · 0 tokens per session scan A 308fb5b68d8d
cue is a command published in the GitHub repository Untrivial-ai/agent-orchestrator (13,060 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 364 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 2026-10-01.
Other commands, from other repositories
firm
Convene your standing AI staff — memos on every beat, a board session without you, minutes with dissent preserved.
cn-career-ladder
A workflow that turns Chinese workplace notes into a promotion case through five stages: weekly reports, a yearly review, a presentation outline, and interview practice. It carries each stage's output into the next.
ship-a-feature
Workflow recipe — take a feature idea from fuzzy brief to launch plan by chaining 5 skills.
cn-campus-offer
A workflow for planning a Chinese university recruitment season, building a Chinese and English CV, and practising technical interviews. Campus recruitment is the process of applying to employers through university-focused hiring rounds.
setup-context
Set up your Skill Memory — a pm-context.md every skill reads so outputs come back tailored to you.
sync-to-copilot
Sync skills and instructions from Claude or Codex to GitHub Copilot CLI.