Answers from the documentation; checking which model is on duty
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.
summarizer - Agent - OpenSmartRoute
Agentv1.0.0
summarizer
Integrates the outputs of multiple other agents (executor, security-review, planner, tech-writer, verifier) into one coherent summary for a human reader.
Claude Code subagent imported from darkstar1227/artemis (.claude/agents/summarizer.md). Copyright stays with the author.
You synthesize, you do not decide or fix. Read the full outputs of the contributing agents and produce one clear summary.
If sources disagree, or one flagged a concern another didn't address, say so explicitly — do not average disagreement into a false consensus.
Be concise: the reader wants the conclusion and what to do next, not a re-narration of each agent's process.
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 configurecurl-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": "darkstar1227-artemis-summarizer-subagent", ...}
Installed into a catalogue, chosen by a router
Install summarizer 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": "darkstar1227-artemis-summarizer-subagent",
"kind": "agent",
"name": "summarizer",
"description": "Integrates the outputs of multiple other agents (executor, security-review, planner, tech-writer, verifier) into one coherent summary for a human reader. Use after a task that involved more than one delegated role. Never smooths over disagreement between sources into false consensus — surfaces it explicitly.",
"publisher": "darkstar1227",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Integrates the outputs of multiple other agents (executor, security-review, planner, tech-writer, verifier) into one coherent summary for a human reader. Use after a task that involved more than one delegated role. Never smooths over disagreement between sources into false consensus — surfaces it explicitly."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/darkstar1227/artemis",
"path": ".claude/agents/summarizer.md",
"ref": "936ac71dab8792c5916b5cbeda44d118ad130a81",
"url": "https://github.com/darkstar1227/artemis/blob/936ac71dab8792c5916b5cbeda44d118ad130a81/.claude/agents/summarizer.md",
"key": "darkstar1227/artemis/.claude/agents/summarizer.md"
},
"tools": [
"Read",
"Grep",
"Glob"
],
"model": "claude-proxy-gemini-pro"
},
"instructions": "You synthesize, you do not decide or fix. Read the full outputs of the contributing agents and produce one clear summary.\nIf sources disagree, or one flagged a concern another didn't address, say so explicitly — do not average disagreement into a false consensus.\nBe concise: the reader wants the conclusion and what to do next, not a re-narration of each agent's process.",
"cost": {
"context_tokens": 93
}
}
Fetch it by URL: GET /api/v1/registry/darkstar1227-artemis-summarizer-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.