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.

claude-codex-foundry - Skill

Name: claude-codex-foundry
Author: msftse-org

Imported from msftse-org/claude-codex-foundry (AGENTS.md). Install upstream with npx skills add msftse-org/claude-codex-foundry. Copyright stays with the author.

Working in this repository

For a fresh customer deployment, read the LLM deployment and onboarding runbook first. It includes a customer input checklist, a prompt to hand to an assistant, the supported deployment commands, user import, verification and handover. Use the checked-out scripts and their --help as the command reference.

For repository changes, follow CONTRIBUTING.md. Preserve unrelated work and customer files. Run the relevant offline checks; a request to edit or review code does not authorize deploying Azure resources.

Keep each customer's configuration, identity lists, reports and installer bundles in a separate checkout, under ignored .local/ and dist/. Never commit credentials or customer data. Do not copy another customer's deployment state to start a new installation.

The one-command deployment defaults to unified Claude/Codex administration, including the shared runtime. Read docs/unified-administration.md for model-policy verification, owner publication and the portal-only upgrade command. Inference remains closed until reviewed model bounds and access policy are configured. Use portal.mode=baseline only for an explicitly requested legacy Claude-only portal. Preserve existing ledgers and complete the runtime acceptance checks before claiming customer spending guarantees.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Install claude-codex-foundry 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.

{ "ocm": "1", "id": "msftse-org-claude-codex-foundry-claude-codex-foundry", "kind": "skill", "name": "claude-codex-foundry", "description": "For a fresh customer deployment, read [the LLM deployment and onboarding runbook](docs/llm-onboarding.md) first. It includes a customer input checklist, a prompt to hand to an assistant, the supported deployment commands, user import, verification and handover. Use the checked-out scripts and their `--help` as the command reference.", "publisher": "msftse-org", "version": "1.0.0", "capabilities": { "domains": [ "customer_support", "hr" ], "tags": [ "skill-md", "github-agents" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "For a fresh customer deployment, read [the LLM deployment and onboarding runbook](docs/llm-onboarding.md) first. It includes a customer input checklist, a prompt to hand to an assistant, the supported deployment commands, user import, verification and handover. Use the checked-out scripts and their `--help` as the command reference." ], "primary": false, "metadata": { "source": { "provider": "github-agents", "repository": "https://github.com/msftse-org/claude-codex-foundry", "path": "AGENTS.md", "ref": "110a578c7783c99d808817752b1d8712244c7f86", "url": "https://github.com/msftse-org/claude-codex-foundry/blob/110a578c7783c99d808817752b1d8712244c7f86/AGENTS.md", "key": "msftse-org/claude-codex-foundry/AGENTS.md" } }, "instructions": "# Working in this repository\n\nFor a fresh customer deployment, read [the LLM deployment and onboarding runbook](docs/llm-onboarding.md) first. It includes a customer input checklist, a prompt to hand to an assistant, the supported deployment commands, user import, verification and handover. Use the checked-out scripts and their `--help` as the command reference.\n\nFor repository changes, follow [CONTRIBUTING.md](CONTRIBUTING.md). Preserve unrelated work and customer files. Run the relevant offline checks; a request to edit or review code does not authorize deploying Azure resources.\n\nKeep each ", "cost": { "context_tokens": 342 } }

claude-codex-foundry

About

Working in this repository

Use it

Install claude-codex-foundry 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