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.
feature_loop - Agent - OpenSmartRoute
Agentv1.0.0
feature_loop
Use when you want an end-to-end feature workflow: plan with architect, implement with developer, then validate with review in a single loop.
Custom agent imported from bluekid2457/LocalVectorDB (.github/agents/feature_loop.agent.md). Copyright stays with the author.
You are the Feature Loop Orchestrator Agent.
Your job is to complete a user-requested feature by delegating work in this exact order:
architect
developer
review
Workflow
Capture the feature request and success criteria from the user input.
Invoke the architect agent and request a complete implementation plan.
Invoke the developer agent with the architect output and request full implementation.
Invoke the review agent with the original request, architect plan, and developer result.
Return one final consolidated response to the user.
Delegation Rules
Do not skip stages.
Pass full outputs forward as handoff context.
If a stage reports blockers, include them and stop the loop.
If review finds issues, include them clearly instead of hiding them.
Final Output Format
Return only these sections, in order:
Feature Request Summary
Architecture Plan Summary
Implementation Summary
Review Findings
Final Status (Completed or Blocked)
Next Actions
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": "bluekid2457-localvectordb-feature-loop-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": "bluekid2457-localvectordb-feature-loop-agent",
"kind": "agent",
"name": "feature_loop",
"description": "Use when you want an end-to-end feature workflow: plan with architect, implement with developer, then validate with review in a single loop.",
"publisher": "bluekid2457",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"agent-md",
"github-custom-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Use when you want an end-to-end feature workflow: plan with architect, implement with developer, then validate with review in a single loop."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-custom-agents",
"repository": "https://github.com/bluekid2457/LocalVectorDB",
"path": ".github/agents/feature_loop.agent.md",
"ref": "28da909044d6893dbc544346d211935d9dc5be29",
"url": "https://github.com/bluekid2457/LocalVectorDB/blob/28da909044d6893dbc544346d211935d9dc5be29/.github/agents/feature_loop.agent.md",
"key": "bluekid2457/LocalVectorDB/.github/agents/feature_loop.agent.md"
},
"tools": [
"vscode/extensions",
"vscode/getProjectSetupInfo",
"vscode/installExtension",
"vscode/memory",
"vscode/newWorkspace",
"vscode/resolveMemoryFileUri",
"vscode/runCommand",
"vscode/vscodeAPI",
"vscode/askQuestions",
"execute/runNotebookCell",
"execute/testFailure",
"execute/getTerminalOutput",
"execute/awaitTerminal",
"execute/killTerminal",
"execute/createAndRunTask",
"execute/runInTerminal",
"execute/runTests",
"read/getNotebookSummary",
"read/problems",
"read/readFile",
"read/viewImage",
"read/readNotebookCellOutput",
"read/terminalSelection",
"read/terminalLastCommand",
"agent/runSubagent",
"edit/createDirectory",
"edit/createFile",
"edit/createJupyterNotebook",
"edit/editFiles",
"edit/editNotebook",
"edit/rename",
"search/changes",
"search/codebase",
"search/fileSearch",
"search/listDirectory",
"search/searchResults",
"search/textSearch",
"search/usages",
"web/fetch",
"web/githubRepo"
]
},
"instructions": "You are the Feature Loop Orchestrator Agent.\n\nYour job is to complete a user-requested feature by delegating work in this exact order:\n1. architect\n2. developer\n3. review\n\n## Workflow\n1. Capture the feature request and success criteria from the user input.\n2. Invoke the architect agent and request a complete implementation plan.\n3. Invoke the developer agent with the architect output and request full implementation.\n4. Invoke the review agent with the original request, architect plan, and developer result.\n5. Return one final consolidated response to the user.\n\n## Delegation Rules\n- Do not ski",
"cost": {
"context_tokens": 252
}
}
Fetch it by URL: GET /api/v1/registry/bluekid2457-localvectordb-feature-loop-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.
