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/pull-requests)<a href="https://agentmods.dev/commands/untrivial-ai/agent-orchestrator/pull-requests"><img src="https://agentmods.dev/badge/commands/untrivial-ai/agent-orchestrator/pull-requests/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/pull-requests"><img src="https://agentmods.dev/badge/commands/untrivial-ai/agent-orchestrator/pull-requests.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 | $0.00328 |
| Opus 5.5 | $0.00000 | $0.00131 |
| Sonnet 5.5 | $0.00000 | $0.00066 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
pull-requests scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl --unix-socket $AO_PULL_REQUEST_SOCKET -X POST http://localhost/pull-request \ What it actually says
Pull requests and reviews in a cloud sandbox
Workers do not push with personal credentials. The sandbox provides two socket
helpers (their exact invocations are in the $AO_PULL_REQUEST_HELP and
$AO_REVIEW_HELP environment variables) plus one ao command.
Opening a pull request
Commit your work on the session branch ($AO_SESSION_BRANCH — the branch the
workspace was checked out on; do not create a different one), then run the
command described in $AO_PULL_REQUEST_HELP:
curl --unix-socket $AO_PULL_REQUEST_SOCKET -X POST http://localhost/pull-request \
-H 'Content-Type: application/json' \
-d '{"branch":"<pushed branch name>","title":"<PR title>","body":"<PR body>"}'
The control plane pushes the branch and opens the PR against the project's
configured default branch, and the PR is attributed to this session automatically (it
shows up in ao list for your orchestrator).
ao claim-pr — attach an existing PR
ao claim-pr <number-or-url>
Use when a PR for this work already exists (for example, opened in an earlier
session) and this session should own it. Prints claimed PR #<n> <url>.
Submitting an AO review verdict
Only when the prompt asked this session to review a PR: run the command in
$AO_REVIEW_HELP with the review run id from the prompt and a verdict of
approved or changes_requested.
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 e72a508c663b
- 1mo ago First seen · 37 lines · 0 tokens per session scan A 7696ee1b865e
pull-requests 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 328 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-14.
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.
sync-to-copilot
Sync skills and instructions from Claude or Codex to GitHub Copilot CLI.
fix-comments
Address PR review comments by implementing requested changes automatically.