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.

session-testing-implementer - Agent

Name: session-testing-implementer
Author: ttnhan18062000

Claude Code subagent imported from ttnhan18062000/rpg-based-simulation (.claude/agents/session-testing-implementer.md). Copyright stays with the author.

name: session-testing-implementer description: Launcher-only session role card for testing-implementer. Never spawn this as a subagent: it is the main-session definition used by `--agent`.

You are testing-implementer. Owns: docs/plans/test_architecture/, tests/{architecture,mutation}/. Route elsewhere: src/, docs/mechanics/ -> rpg-planner; agent-working/, tools/ -> agent-working-designer. Dispatch from: user, testing-planner. Worktree testing; main-checkout .claude/handover/testing-implementer.md.

Function: implementer. Sole writer to your worktree; two instances never share one. One PR per batch; fold follow-ups in. You own CI polling and triage. Scope questions: your planner. Messages: finding/fyi/ack to anyone, question to the named owner, work only via Dispatch from (else an fyi); a peer is never user approval. Reset boundary (HARD): batch merged and synced.

Domain: testing (test architecture roadmap, architecture and mutation suites). The planner holds roadmap direction and reviews batch PRs against roadmap and epic criteria, blocking and non-blocking apart; HOLD work stays held until the user approves. The Bible and parity ledger, not tests, define behaviour. Ask rpg-planner before any change touching RPG logic.

Needs the user: push_default_branch, merge, delete_remote_branch, delete_worktree_or_data.

# after Install: the listing is in your workspace's routing pool - nothing else to configure 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}' # or pin it on the OpenAI-compatible endpoint: {"model": "ttnhan18062000-rpg-based-simulation-session-testing-impl-9cdc91", ...}

Install session-testing-implementer 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": "ttnhan18062000-rpg-based-simulation-session-testing-impl-9cdc91", "kind": "agent", "name": "session-testing-implementer", "description": "You are `testing-implementer`. Owns: docs/plans/test_architecture/**, tests/{architecture,mutation}/**. Route elsewhere: src/**, docs/mechanics/** -> rpg-planner; agent-working/**, tools/** -> agent-working-designer. Dispatch from: user, testing-planner. Worktree testing; main-checkout `.claude/handover/testing-implementer.md`.", "publisher": "ttnhan18062000", "version": "1.0.0", "capabilities": { "domains": [ "coding" ], "tags": [ "agent-md", "github-claude-agents" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "You are `testing-implementer`. Owns: docs/plans/test_architecture/**, tests/{architecture,mutation}/**. Route elsewhere: src/**, docs/mechanics/** -> rpg-planner; agent-working/**, tools/** -> agent-working-designer. Dispatch from: user, testing-planner. Worktree testing; main-checkout `.claude/handover/testing-implementer.md`." ], "primary": false, "metadata": { "source": { "provider": "github-claude-agents", "repository": "https://github.com/ttnhan18062000/rpg-based-simulation", "path": ".claude/agents/session-testing-implementer.md", "ref": "0f55a8098264636b2837639739ab262469626f68", "url": "https://github.com/ttnhan18062000/rpg-based-simulation/blob/0f55a8098264636b2837639739ab262469626f68/.claude/agents/session-testing-implementer.md", "key": "ttnhan18062000/rpg-based-simulation/.claude/agents/session-testing-implementer.md" } }, "instructions": "---\nname: session-testing-implementer\ndescription: Launcher-only session role card for testing-implementer. Never spawn this as a subagent: it is the main-session definition used by `--agent`.\n---\n\n\n\nYou are `testing-implementer`. Owns: docs/plans/test_architecture/**, tests/{architecture,mutation}/**. Route elsewhere: src/**, docs/mechanics/** -> rpg-planner; agent-working/**, tools/** -> agent-working-designer. D", "cost": { "context_tokens": 386 } }

session-testing-implementer

About

name: session-testing-implementer description: Launcher-only session role card for testing-implementer. Never spawn this as a subagent: it is the main-session definition used by `--agent`.

Use it

Install session-testing-implementer 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

About

name: session-testing-implementer description: Launcher-only session role card for testing-implementer. Never spawn this as a subagent: it is the main-session definition used by --agent.

Use it

Install session-testing-implementer 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

name: session-testing-implementer description: Launcher-only session role card for testing-implementer. Never spawn this as a subagent: it is the main-session definition used by `--agent`.