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/send)<a href="https://agentmods.dev/commands/untrivial-ai/agent-orchestrator/send"><img src="https://agentmods.dev/badge/commands/untrivial-ai/agent-orchestrator/send/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/send"><img src="https://agentmods.dev/badge/commands/untrivial-ai/agent-orchestrator/send.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 | $0.00540 |
| Opus 5.5 | $0.00000 | $0.00216 |
| Sonnet 5.5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
send 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 1mo 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:
- send — 92% identical, 45 lines differ
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ao send
Send a message to a running agent session. Use this to correct or direct a live agent mid-stream without killing and respawning it.
Syntax
ao send [flags]
Flags
| Flag | Meaning | Default / Required |
|---|---|---|
--message string |
Message body | Required unless --recover-only |
--session string |
Session id | Required |
--steer |
Add guidance to the active Chat turn, or start a normal turn when idle | Optional |
--client-message-id string |
Stable delivery handle for steering and safe retries | Generated automatically with --steer |
--recover-only |
Recover the outcome for an existing delivery handle without resending | Requires --steer and --client-message-id |
Steering and recovery
--steer uses one atomic daemon operation. If the session has an active Chat
turn, the message is added to that turn. If the session is idle, the message
starts a normal Chat turn. The state cannot change between those decisions and
leave the message queued as a separate correction.
Every steering request has a client message id. Supply one explicitly when a caller must retain the handle across retries:
ao send --session mer-3 --steer --client-message-id correction-42 --message "Focus only on the backend."
If the command reports an uncertain outcome or a transport failure, preserve the delivery handle printed in the error. Recover the existing result without contacting the provider again:
ao send --session mer-3 --steer --recover-only --client-message-id correction-42
Do not invent a new client message id after an uncertain result. Reusing the original id lets the daemon return the durable steering receipt or normal turn without delivering the message twice. Recovery confirms the recorded delivery outcome, not that the agent acted on the guidance.
Examples
# Send a correction to a running session
ao send --session mer-3 --message "Focus only on the backend; ignore frontend files."
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.
- 1mo ago Changed · +35 lines 519e375414d7
- 1mo ago First seen · 29 lines · 0 tokens per session scan A 9a77256fab96
send is a command published in the GitHub repository Untrivial-ai/agent-orchestrator (13,307 stars, last pushed 6d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 540 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-all
Sync skills, commands, MCP servers, and preferences between Claude, Codex, Copilot, and Cursor in one operation.
sync-to-cursor
Sync skills, commands, agents, hooks, rules, and MCP from Claude, Codex, or Copilot to Cursor IDE.
skill-diff
Compare a skill across Claude, Codex, Copilot, and Cursor to show differences.
sync-to-copilot
Sync skills and instructions from Claude or Codex to GitHub Copilot CLI.
skill-trace-status
Check skill loading status and instrumentation across CLI environments.
sync-from-copilot
Sync skills and instructions from GitHub Copilot CLI to Claude, Codex, or Cursor.