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.
npx agentmods add rules/verbalize-public/open-delegate/open-delegate-routinggit clone --depth 1 https://github.com/Verbalize-public/open-delegateWhat 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 | $0.00359 | $0.00359 |
| Opus 5 | $0.00179 | $0.00179 |
| Sonnet 5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
open-delegate-routing 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 2d 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
open-delegate routing
Prefer cheaper OpenCode alternatives when delegating work out of the current Cursor chat.
When to use ode_delegate (+ ode_await)
If a persona / Task request names a model that is:
- in ODE_MODELS — the built-in cheap force catalog, or whatever
OPEN_DELEGATE_ODE_MODELS/ the liveode_delegatetool description lists, or - an OpenCode id starting with
openrouter/,
you must call ode_delegate then ode_await (or ode_await with timeoutMs: 0 for a peek), not the native Task / subagent tool.
Pass the OpenCode provider/model id as-is. Do not invent Cursor-slug remaps and do not “helpfully” upgrade to Anthropic/OpenAI flagships (Opus, Sonnet, Fable, GPT Sol/Terra).
When to prefer native Task
Use the native Task / subagent tool only when the named model is Cursor-native and not on the ODE_MODELS force list.
How to drive the bridge
Follow skill ode-delegate for the core loop (ode_delegate → ode_await → transcript / resume via ode_delegate({ sessionId }) / cancel). Omit model to use OPEN_DELEGATE_DEFAULT_MODEL or the OpenCode server default (prefer a cheap Zen free pin when configuring). Optional waitMs on ode_delegate can collapse short tasks into one tool call.
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.
- 2d ago First seen · 28 lines · 359 tokens per session scan A 67f3b21d2319
open-delegate-routing is a cursor rule published in the GitHub repository Verbalize-public/open-delegate (1 stars, last pushed 1mo ago), licensed MIT. It adds 359 tokens to every session, about $0.0018 per session on Opus 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 2026-08-31.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.