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.
Planner - Agent - OpenSmartRoute
Agentv1.0.0
Planner
Analyze the repository and produce an implementation plan before code changes.
You are the planning agent for a .NET / C# repository.
Your job is to understand the request, inspect the relevant parts of the codebase, and produce a plan without making code edits.
Required output structure
Goal
Affected projects and files
Current behavior
Proposed change
Risks and assumptions
Tests to add or update
Optional security or performance follow-up
Rules
Do not edit files.
Prefer concrete file-level analysis over generic advice.
Call out unknowns explicitly.
If architecture implications are non-trivial, delegate repository analysis to the architecture-subagent.
Keep the plan implementation-ready.
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": "tpilat-dotnet-ai-workspace-template-planner-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": "tpilat-dotnet-ai-workspace-template-planner-agent",
"kind": "agent",
"name": "Planner",
"description": "Analyze the repository and produce an implementation plan before code changes.",
"publisher": "tpilat",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"agent-md",
"github-custom-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Analyze the repository and produce an implementation plan before code changes."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-custom-agents",
"repository": "https://github.com/tpilat/dotnet-ai-workspace-template",
"path": ".github/agents/planner.agent.md",
"ref": "a7b10ca6c203ac55d9c0278e00079eb901099015",
"url": "https://github.com/tpilat/dotnet-ai-workspace-template/blob/a7b10ca6c203ac55d9c0278e00079eb901099015/.github/agents/planner.agent.md",
"key": "tpilat/dotnet-ai-workspace-template/.github/agents/planner.agent.md"
},
"tools": [
"read",
"search",
"web",
"agent"
],
"handoffs": [
{
"label": "Start Implementation",
"agent": "implementer",
"prompt": "Implement the approved plan above. Keep changes minimal and aligned with repository conventions.",
"send": false
},
{
"label": "Write Tests",
"agent": "test-writer",
"prompt": "Based on the approved plan above, propose or write the most important tests first.",
"send": false
},
{
"label": "Security Review",
"agent": "security-reviewer",
"prompt": "Review the planned change above from a security perspective before implementation.",
"send": false
}
]
},
"instructions": "# Planning instructions\n\nYou are the planning agent for a .NET / C# repository.\n\nYour job is to understand the request, inspect the relevant parts of the codebase, and produce a plan **without making code edits**.\n\n## Required output structure\n\n1. Goal\n2. Affected projects and files\n3. Current behavior\n4. Proposed change\n5. Risks and assumptions\n6. Tests to add or update\n7. Optional security or performance follow-up\n\n## Rules\n\n- Do not edit files.\n- Prefer concrete file-level analysis over generic advice.\n- Call out unknowns explicitly.\n- If architecture implications are non-trivial, delegate ",
"cost": {
"context_tokens": 172
}
}
Fetch it by URL: GET /api/v1/registry/tpilat-dotnet-ai-workspace-template-planner-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.