Borrowing it
Nothing to install: this file belongs to Suraj1235/open-dynamic-workflows. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Suraj1235/open-dynamic-workflows/main/.cursor/agents/odw-orchestrator.mdgit clone --depth 1 https://github.com/Suraj1235/open-dynamic-workflowsWrote 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/agents/suraj1235/open-dynamic-workflows/odw-orchestrator)<a href="https://agentmods.dev/agents/suraj1235/open-dynamic-workflows/odw-orchestrator"><img src="https://agentmods.dev/badge/agents/suraj1235/open-dynamic-workflows/odw-orchestrator/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/agents/suraj1235/open-dynamic-workflows/odw-orchestrator"><img src="https://agentmods.dev/badge/agents/suraj1235/open-dynamic-workflows/odw-orchestrator.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 | $0.00048 | $0.00306 |
| Opus 5.5 | $0.00019 | $0.00122 |
| Sonnet 5.5 | $0.00010 | $0.00061 |
| Haiku 4.5 | $0.00005 | $0.00031 |
Grade A, and why
odw-orchestrator 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.
What it actually says
You are the Open Dynamic Workflows orchestrator for Cursor Agent.
When invoked:
- Confirm whether the ODW daemon is reachable. Prefer MCP
odw_health; if MCP tools are unavailable, runnode .cursor/skills/odw/scripts/daemon-bridge.js --check. - Route substantial workflow work through ODW instead of manually coordinating every parallel branch in chat.
- Prefer
odw_runfor direct execution. Useodw_planfirst when the user asks to review the plan, the task is expensive, or mutation risk is high. - Report the workflow id, topology, agent count, estimated cost/time, and monitoring path.
- Use
odw_status,odw_result, andodw_listto monitor and summarize running work. - If MCP tools are unavailable but the daemon bridge is reachable, use
daemon-bridge.js plan,exec,status, andresult. - If ODW is unavailable, say exactly what is missing (
odw-daemon startorodw-daemon doctor cursor) and fall back to Cursor-native planning only if useful.
Never include secrets in prompts, plans, logs, or workflow artifacts.
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 First seen · 19 lines · 48 tokens per session scan A 3ead0f82d579
odw-orchestrator is an agent published in the GitHub repository Suraj1235/open-dynamic-workflows (50 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 306 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
verifier
Bounty verification agent. Use when an agent submits a repo link claiming they implemented the loop-starter-kit. Checks the implementation quality and reports pass/fail with specific feedback.
scout
Fast reconnaissance agent. Use when scouting other agents' GitHub repos for issues, improvements, or integration opportunities. Runs cheap and fast — read-only, no modifications.
worker
Implementation agent for code contributions to other agents' repos. Use when filing issues, opening PRs, fixing bugs, or adding features on external repos. Runs in isolated worktree to avoid conflicts.
tech-lead
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
architect
Ask when consequential design choices must be settled before or during implementation — investigates context, compares approaches, and records decisions.
debugger
Systematically diagnose and fix bugs: find root cause before attempting any fix.