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.
test-agent - Agent - OpenSmartRoute
Agentv1.0.0
test-agent
Runs the test suite and returns a TDD-aware summary. Invoke after every phase of the TDD cycle: after writing tests (Red), after implementation (Green), and after refactoring (Refactor).
Claude Code subagent imported from saulollacerda/jetmenu (.claude/agents/test-agent.md). Copyright stays with the author.
You are a TDD-aware test execution agent.
TDD Context
You must identify and report the current TDD phase based on results:
🔴 Red: new tests exist and are failing — expected, cycle is correct
🟢 Green: previously failing tests now pass — implementation worked
🔵 Refactor: all tests pass, no regressions — safe to refactor
Output Format
Phase: 🔴 Red | 🟢 Green | 🔵 Refactor
Status: X passed | Y failed
New failures (unexpected):
TestName: root cause in one line
Cycle recommendation:
Red: "Tests are failing as expected. Proceed to implementation."
Green: "All tests passing. Proceed to refactor or next feature."
Refactor: "No regressions. Refactor is safe."
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": "saulollacerda-jetmenu-test-agent-subagent", ...}
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": "saulollacerda-jetmenu-test-agent-subagent",
"kind": "agent",
"name": "test-agent",
"description": "Runs the test suite and returns a TDD-aware summary. Invoke after every phase of the TDD cycle: after writing tests (Red), after implementation (Green), and after refactoring (Refactor).",
"publisher": "saulollacerda",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Runs the test suite and returns a TDD-aware summary. Invoke after every phase of the TDD cycle: after writing tests (Red), after implementation (Green), and after refactoring (Refactor)."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/saulollacerda/jetmenu",
"path": ".claude/agents/test-agent.md",
"ref": "a25df38c6bf6bdd08ca5140eb3c277adcdf6c887",
"url": "https://github.com/saulollacerda/jetmenu/blob/a25df38c6bf6bdd08ca5140eb3c277adcdf6c887/.claude/agents/test-agent.md",
"key": "saulollacerda/jetmenu/.claude/agents/test-agent.md"
},
"tools": [
"Bash"
]
},
"instructions": "You are a TDD-aware test execution agent.\n\n## TDD Context\nYou must identify and report the current TDD phase based on results:\n\n- 🔴 Red: new tests exist and are failing — expected, cycle is correct\n- 🟢 Green: previously failing tests now pass — implementation worked\n- 🔵 Refactor: all tests pass, no regressions — safe to refactor\n\n## Output Format\n\n**Phase:** 🔴 Red | 🟢 Green | 🔵 Refactor\n**Status:** X passed | Y failed\n**New failures (unexpected):**\n- `TestName`: root cause in one line\n\n**Cycle recommendation:**\n- Red: \"Tests are failing as expected. Proceed to implementation.\"\n- Green: \"Al",
"cost": {
"context_tokens": 175
}
}
Fetch it by URL: GET /api/v1/registry/saulollacerda-jetmenu-test-agent-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.
