How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

crg-calc - Prompt - OpenSmartRoute

Promptv1.0.0

crg-calc

Name: crg-calc
Author: ITriskMgr

Compute CyberRiskGuardian KRIs for one scenario

by ITriskMgr(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Prompt file imported from ITriskMgr/CyberRiskGuardian (.claude/commands/crg-calc.md). Fill in {{arguments}} before use. Copyright stays with the author.

Compute the CyberRiskGuardian indicators for the scenario parameters in: {{arguments}}

Use the crg-calculator MCP tool crg_risk if available; otherwise run python3 with the crg_calc module from the crg-quantify skill's scripts/ directory. Default appetite 0.30 and factor 1,000 unless given. Show the formula substitution, estimated, tolerated, mitigated and residual risk, the residual-to-tolerated ratio, the classification (below / approximately at / above tolerance), the CVSS v4.0 score and severity, and a one-line interpretation. Remind that Residual/Tolerated depends only on damage, reductions and appetite.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

Compute the CyberRiskGuardian indicators for the scenario parameters in: {{arguments}}

Use the `crg-calculator` MCP tool `crg_risk` if available; otherwise run `python3` with the `crg_calc` module from the `crg-quantify` skill's `scripts/` directory. Default appetite 0.30 and factor 1,000 unless given. Show the formula substitution, estimated, tolerated, mitigated and residual risk, the residual-to-tolerated ratio, the classification (below / approximately at / above tolerance), the CVSS v4.0 score and severity, and a one-line interpretation. Remind that Residual/Tolerated depends only on damage, reductions and appetite.

Installed into a catalogue, chosen by a router

Install crg-calc and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

For the business

What it costs to adopt - in engineering time.

Same client, same code
One base URL
The OpenAI-compatible endpoint answers your existing SDK calls; model=auto lets the router choose.
The SDKs
One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
Next eligible model answers
Failover built in
When a provider is down or over quota the request moves on; the trace says it did.

Manifest

The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.

itriskmgr-cyberriskguardian-crg-calc-command.prompt.jsonjson

{
  "prompt": "Compute the CyberRiskGuardian indicators for the scenario parameters in: {{arguments}}\n\nUse the `crg-calculator` MCP tool `crg_risk` if available; otherwise run `python3` with the `crg_calc` module from the `crg-quantify` skill's `scripts/` directory. Default appetite 0.30 and factor 1,000 unless given. Show the formula substitution, estimated, tolerated, mitigated and residual risk, the residual-to-tolerated ratio, the classification (below / approximately at / above tolerance), the CVSS v4.0 score and severity, and a one-line interpretation. Remind that Residual/Tolerated depends only on damage, reductions and appetite.",
  "variables": [
    "arguments"
  ],
  "notes": "Compute CyberRiskGuardian KRIs for one scenario Arguments: PbA Pbx de dm theta mu red_p red_i CVSS-vector [appetite] [factor].",
  "metadata": {
    "source": {
      "provider": "github-claude-commands",
      "repository": "https://github.com/ITriskMgr/CyberRiskGuardian",
      "path": ".claude/commands/crg-calc.md",
      "ref": "2205f3197756bda183575a6f7d3d2451ee6aeb47",
      "url": "https://github.com/ITriskMgr/CyberRiskGuardian/blob/2205f3197756bda183575a6f7d3d2451ee6aeb47/.claude/commands/crg-calc.md",
      "key": "ITriskMgr/CyberRiskGuardian/.claude/commands/crg-calc.md"
    }
  }
}

Fetch it by URL: GET /api/v1/registry/itriskmgr-cyberriskguardian-crg-calc-command/manifest?version=1.0.0

About

Use it

Install crg-calc and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Manifest

Reviews