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.
TestRunner - Agent - OpenSmartRoute
Agentv1.0.0
TestRunner
Runs the project test suite and produces a structured summary of results. Use instead of running tests directly in the main agent to avoid test output consuming the primary context window — critical f
Run the test command specified in the project's AGENTS.md file.
Do NOT output the full test log. Only output the structured summary.
This preserves the parent agent's context window for implementation
work.
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": "ai-digital-architect-github-copilot-test-runner-agent", ...}
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
{
"ocm": "1",
"id": "ai-digital-architect-github-copilot-test-runner-agent",
"kind": "agent",
"name": "TestRunner",
"description": "Runs the project test suite and produces a structured summary of results. Use instead of running tests directly in the main agent to avoid test output consuming the primary context window — critical for long-running iterative workflows.",
"publisher": "ai-digital-architect",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"agent-md",
"github-custom-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Runs the project test suite and produces a structured summary of results. Use instead of running tests directly in the main agent to avoid test output consuming the primary context window — critical for long-running iterative workflows."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-custom-agents",
"repository": "https://github.com/ai-digital-architect/github-copilot",
"path": ".github/agents/test-runner.agent.md",
"ref": "5f587026d44dd2389c4b9147360efd25d0146fe1",
"url": "https://github.com/ai-digital-architect/github-copilot/blob/5f587026d44dd2389c4b9147360efd25d0146fe1/.github/agents/test-runner.agent.md",
"key": "ai-digital-architect/github-copilot/.github/agents/test-runner.agent.md"
},
"tools": [
"terminalLastCommand",
"codebase"
]
},
"instructions": "Run the project test suite and return a structured JSON summary:\n\n```json\n{\n \"passed\": 0,\n \"failed\": 0,\n \"skipped\": 0,\n \"errors\": 0,\n \"failures\": [\n {\n \"test\": \"<test name>\",\n \"file\": \"<file path>\",\n \"message\": \"<failure message (first 200 chars)>\",\n \"type\": \"assertion|runtime|timeout\"\n }\n ],\n \"all_passing\": false\n}\n```\n\nRun the test command specified in the project's `AGENTS.md` file.\n\nDo NOT output the full test log. Only output the structured summary.\nThis preserves the parent agent's context window for implementation\nwork.",
"cost": {
"context_tokens": 141
}
}
Fetch it by URL: GET /api/v1/registry/ai-digital-architect-github-copilot-test-runner-agent/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.
