· 1 observation
Technical updates · 1
Package or technical metadata updated
View technical comparison →Orbral v0.1.5
Pick the most efficient model
From the developer
Not specified in the available declarations: limitations, pricing & account requirements.
Research, plan, and build a support dashboard. Route each phase to a model and name its verifier.
Developer declarations; not independently tested. Listing last checked Nov 11, 2026. Package observed Nov 10, 2026.
From the marketplace listing
Use Local Model Route Planner when different parts of a job need different models or agents. It weighs quality, capability, risk, cost, and verification needs, then returns an inspectable plan with selected routes, rejected alternatives, and independent review where needed. It plans the route; it does not call a provider or prove that work ran.
Language: English · Automatically detected from descriptions.
Exact text from the indicated source. A mention alone does not establish support for your task.
Plan from a local model and agent registry Choose the lowest-cost eligible route Explain rejected options Require independent high-risk review Never call a provider
model-routing model-selection agent-orchestration cost-control quality-gates independent-review routing-policy codex
· 1 observation
Package or technical metadata updated
View technical comparison →· 2 observations
Package or technical metadata updated
View technical comparison →· 2 observations
Package or technical metadata updated
View technical comparison →Package or technical metadata updated
View technical comparison →Find competitors to follow as you develop your plugin.
Recommends and compares AI models (LLMs) for a task, with list prices, context windows and measured scores in 30 languages. Read-only, no...
Shared terms: pick, model, cost, job
Every leading model inside Codex, with each turn routed to the model that does it best so your plan lasts longer.
Shared terms: model, cost, pick, provider
Read the last published AI model metadata catalog with timestamps and freshness. Catalog lookup only; no model execution, quality guarant...
Shared terms: model, execution, quality
Choose Codex models with local rules in a separate Windows task window.
Shared terms: model, local, choose
Keep Codex in the lead with bounded model reviews, benchmark research, and native public-web research.
Shared terms: model, cost, local, provider
--- name: agent-routekit description: "Use before execution with a local route registry. Choose the lowest-cost eligible model or agent plan, explain rejected options, require independent review for high-risk work, and emit planning evidence without calling a provider or claiming the route ran." --- # Local Model Route Planner Local Model Route Planner is a planning and evidence skill. It does not invoke a model runtime or grant execution authority. ## Procedure 1. Translate the task into the task schema shown in `../../examples/`, preserving the user’s risk and quality requirements. Do not down-classify risk to obtain a cheaper route. 2. Use the plugin’s `../../routes.example.json` unless the user supplies a registry. Treat model and effort values as labels whose availability must be verified by the host environment. 3. Validate the registry before relying on it: ```text python <plugin-root>/scripts/routekit.py validate-registry --registry <registry.json> ``` 4. Validate the task. Unknown fields are rejected so a misspelled requirement cannot be ignored: ```text python <plugin-root>/scripts/routekit.py validate-task --task <task.json> ``` 5. Plan the route and retain the receipt: ```text python <plugin-root>/scripts/routekit.py plan --registry <registry.json> --task <task.json> --format json --output <receipt.json> ``` 6. Explain the selected executor, any verifier, the binding quality/risk constraints, and important rejected alternatives. 7. If the host can delegate, execute only within the user’s existing authority and record separate runtime evidence. Never present the planning receipt as proof that the selected model actually ran. 8. Reconcile an outcome only from independently supplied evidence with matching decision and route IDs. Do not infer causation or fabricate missing metrics. ## Fail-closed rules - High- or critical-risk work requires a verifier from a different `independence_group`. - Missing capabilities, invalid configuration, or no eligible route is a blocker, not permission to improvise. - Unknown task or registry fields are validation failures, not ignored extensions. - The least-cost rule applies only after quality, complexity, risk, capability, and independence constraints pass. - Never add credentials, private task data, or internal paths to a public registry or receipt.
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
Some manifest fields differ or could not be read. The structured report retains the source references.
Package observed Nov 10, 2026.
plugins_6a8e59b3dd1881919172e8f2a078b259
Download plugin data (JSON)Plugin details: served from cache. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.