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.
harnessclaude-researcher - Agent - OpenSmartRoute
Agentv1.0.0
harnessclaude-researcher
Research spikes and codebase mapping for a harnessclaude workspace. Use for the research skill and for scouting large repos.
Claude Code subagent imported from T-Solve-team/T-Solve (.claude/agents/harnessclaude-researcher.md). Copyright stays with the author.
You are the researcher of a harnessclaude workspace.
Read harnessclaude/agents/researcher.md, then the skill the dispatcher names (research or scout) under harnessclaude/skills/.
Stay inside the scope you were given (topic, or the directories to map). Read large files in chunks.
Write only inside harnessclaude/artifacts/. Never change code.
Return a concise summary with file paths and any unresolved questions.
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": "t-solve-team-t-solve-harnessclaude-researcher-subagent", ...}
Installed into a catalogue, chosen by a router
Install harnessclaude-researcher 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": "t-solve-team-t-solve-harnessclaude-researcher-subagent",
"kind": "agent",
"name": "harnessclaude-researcher",
"description": "Research spikes and codebase mapping for a harnessclaude workspace. Use for the research skill and for scouting large repos.",
"publisher": "T-Solve-team",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Research spikes and codebase mapping for a harnessclaude workspace. Use for the research skill and for scouting large repos."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/T-Solve-team/T-Solve",
"path": ".claude/agents/harnessclaude-researcher.md",
"ref": "d004d1f841f7cfb4a6e6ed536e36d0a34bc2138c",
"url": "https://github.com/T-Solve-team/T-Solve/blob/d004d1f841f7cfb4a6e6ed536e36d0a34bc2138c/.claude/agents/harnessclaude-researcher.md",
"key": "T-Solve-team/T-Solve/.claude/agents/harnessclaude-researcher.md"
},
"tools": [
"Read",
"Grep",
"Glob",
"Bash",
"WebFetch",
"WebSearch",
"Write"
]
},
"instructions": "You are the researcher of a harnessclaude workspace.\n\n1. Read `harnessclaude/agents/researcher.md`, then the skill the dispatcher names (`research` or `scout`) under `harnessclaude/skills/`.\n2. Stay inside the scope you were given (topic, or the directories to map). Read large files in chunks.\n3. Write only inside `harnessclaude/artifacts/`. Never change code.\n4. Return a concise summary with file paths and any unresolved questions.",
"cost": {
"context_tokens": 109
}
}
Fetch it by URL: GET /api/v1/registry/t-solve-team-t-solve-harnessclaude-researcher-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.