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/automation)<a href="https://agentmods.dev/commands/untrivial-ai/agent-orchestrator/automation"><img src="https://agentmods.dev/badge/commands/untrivial-ai/agent-orchestrator/automation/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/automation"><img src="https://agentmods.dev/badge/commands/untrivial-ai/agent-orchestrator/automation.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 | $0.00776 |
| Opus 5.5 | $0.00000 | $0.00310 |
| Sonnet 5.5 | $0.00000 | $0.00155 |
| Haiku 4.5 | $0.00000 | $0.00078 |
Grade A, and why
automation 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 18d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ao automation
Manage durable recurring session automations through the daemon API.
Syntax
ao automation <subcommand> [args] [flags]
ao automations <subcommand> [args] [flags]
Subcommands
ao automation create
Create a recurring automation for a project.
Syntax:
ao automation create --project <id> --name <name> --prompt <text> (--rrule <rule> | --cron <expr>) [flags]
Flags:
| Flag | Meaning | Default / Required |
|---|---|---|
--project string |
Project id that owns the automation | Required |
--name string |
Display name | Required |
--prompt string |
Session task prompt | Required |
--rrule string |
RFC 5545 recurrence rule | Required unless --cron is set |
--cron string |
Supported five-field cron expression | Required unless --rrule is set |
--timezone string |
IANA timezone | Local zone when resolvable |
--kind string |
Session kind | worker |
--harness string |
Agent harness; empty uses project default | - |
--disabled |
Create disabled | - |
--json |
Print JSON | - |
Example:
ao automation create --project my-app --name "Morning triage" --prompt "Review overnight issues" --cron "0 9 * * *" --timezone America/Los_Angeles
ao automation list
List automations.
Syntax:
ao automation list [flags]
Flags:
| Flag | Meaning | Default / Required |
|---|---|---|
--project string |
Filter by project id | - |
--enabled bool |
Filter by enabled state when present | - |
--json |
Print JSON | - |
ao automation get
Show one automation.
Syntax:
ao automation get <id> [--json]
ao automation update
Update automation metadata, schedule, harness, or enabled state.
Syntax:
ao automation update <id> [flags]
Flags:
| Flag | Meaning |
|---|---|
--name string |
New display name |
--prompt string |
New task prompt |
--rrule string |
Replace schedule with an RRule |
--cron string |
Replace schedule with a cron expression |
--timezone string |
IANA timezone |
--kind string |
Session kind |
--harness string |
Agent harness; empty uses project default |
--enabled bool |
Enable or disable future dispatch |
--json |
Print JSON |
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.
- 18d ago First seen · 129 lines · 0 tokens per session scan A 35d462262559
automation 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 776 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 2026-09-28.
Other commands, from other repositories
sprint-plan
Plan a sprint with a calibrated, realistic commitment.
retro
Run a structured sprint retrospective from notes.
promote
The promote loop — scan your transcripts for what you keep asking, pick a pattern, draft the skill, test its triggers, publish the release package.
reclaim-knowledge
Organize scattered professional material into a domain-based second-brain architecture. Maps existing sources (Canva, Drive, local folders, Notion, screenshots) to functional domains. Non-technical-friendly — produces folder structure + drag-and-drop instructions, not CLI commands.
orchestrate-brain
Weekly 30-minute second-brain review ritual. Orchestrates inbox clear, lightweight distillation, vault maintenance, cross-reference pass, and next-week capture focus. The compounding rhythm that keeps the system alive.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.