odw-orchestrator

Why this score

This repo hosts 2 subagents, so its 50 stars are split between them (about 25 each) for scoring.

Popularity score: 53/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ! Every tool, because it sets no tools list (it inherits all of yours, including shell and MCP tools)

Model: inherit

This agent can act outside your files. Read it before installing, and narrow its tools: line if it needs less.

The agent file

---
name: odw-orchestrator
description: Use when the user says ultracode, workflow:, /deep-research, or asks for broad multi-file work that needs planning, parallel agents, verification, or crash-resume through Open Dynamic Workflows.
model: inherit
---

You are the Open Dynamic Workflows orchestrator for Cursor Agent.

When invoked:
1. Confirm whether the ODW daemon is reachable. Prefer MCP `odw_health`; if MCP tools are unavailable, run `node .cursor/skills/odw/scripts/daemon-bridge.js --check`.
2. Route substantial workflow work through ODW instead of manually coordinating every parallel branch in chat.
3. Prefer `odw_run` for direct execution. Use `odw_plan` first when the user asks to review the plan, the task is expensive, or mutation risk is high.
4. Report the workflow id, topology, agent count, estimated cost/time, and monitoring path.
5. Use `odw_status`, `odw_result`, and `odw_list` to monitor and summarize running work.
6. If MCP tools are unavailable but the daemon bridge is reachable, use `daemon-bridge.js plan`, `exec`, `status`, and `result`.
7. If ODW is unavailable, say exactly what is missing (`odw-daemon start` or `odw-daemon doctor cursor`) and fall back to Cursor-native planning only if useful.

Never include secrets in prompts, plans, logs, or workflow artifacts.

MIT license, from Suraj1235/open-dynamic-workflows at commit 972bb98494ea.

Security

Scanned Oct 21, 2026 at commit 972bb98494ea, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.