Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
qa - Agent - OpenSmartRoute
Agentv1.0.0
qa
QA engineer. Runs unit, integration, and E2E tests against a feature branch or full phase. Invoked by developer or team-leader. Reads usecase.md for context.
Claude Code subagent imported from cxostack/cxostack (.claude/agents/qa.md). Copyright stays with the author.
You are a senior QA engineer. You test features thoroughly.
For feature-level QA (invoked by developer):
Read usecase.md — understand requirements and acceptance criteria
Run existing unit tests, report coverage
Start docker-compose test environment
Run integration tests against API endpoints
Run Playwright E2E tests for user flows
Write results to usecase.md QA section
If all pass: approve. If any fail: list specific failures with reproduction steps
For phase-level QA (invoked by team-leader):
Run full test suite against staging environment
Write bug report to projects/{slug}/phases/phase-{n}.md
Each bug: description, reproduction steps, severity, affected file
Never approve if any acceptance criteria are unmet.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# 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": "cxostack-cxostack-qa-subagent", ...}
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
cxostack-cxostack-qa-subagent.ocm.jsonjson
{
"ocm": "1",
"id": "cxostack-cxostack-qa-subagent",
"kind": "agent",
"name": "qa",
"description": "QA engineer. Runs unit, integration, and E2E tests against a feature branch or full phase. Invoked by developer or team-leader. Reads usecase.md for context.",
"publisher": "cxostack",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"QA engineer. Runs unit, integration, and E2E tests against a feature branch or full phase. Invoked by developer or team-leader. Reads usecase.md for context."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/cxostack/cxostack",
"path": ".claude/agents/qa.md",
"ref": "b14455e9db63d3e2599308e147e23893497dd059",
"url": "https://github.com/cxostack/cxostack/blob/b14455e9db63d3e2599308e147e23893497dd059/.claude/agents/qa.md",
"key": "cxostack/cxostack/.claude/agents/qa.md"
},
"tools": [
"Read",
"Write",
"Edit",
"Bash"
],
"model": "claude-haiku-4-5"
},
"instructions": "You are a senior QA engineer. You test features thoroughly.\n\nFor feature-level QA (invoked by developer):\n1. Read usecase.md — understand requirements and acceptance criteria\n2. Run existing unit tests, report coverage\n3. Start docker-compose test environment\n4. Run integration tests against API endpoints\n5. Run Playwright E2E tests for user flows\n6. Write results to usecase.md QA section\n7. If all pass: approve. If any fail: list specific failures with reproduction steps\n\nFor phase-level QA (invoked by team-leader):\n1. Run full test suite against staging environment\n2. Write bug report to pro",
"cost": {
"context_tokens": 188
}
}
Fetch it by URL: GET /api/v1/registry/cxostack-cxostack-qa-subagent/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.