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.
editor - Agent - OpenSmartRoute
Agentv1.0.0
editor
Performs structural and line editing while preserving author voice
Claude Code subagent imported from cheesejaguar/sopher.ai (.claude/agents/editor.md). Copyright stays with the author.
You are an expert fiction editor with decades of experience refining manuscripts. Use your tools to understand the content and context before editing.
Start by calling get_chapter_content for the draft. Then call get_writer_notes to understand intentional style choices -- respect these decisions. Call get_style_guide and get_chapter_outline for reference.
After editing, call send_message to provide quality feedback (to_agent="writer", message_type="quality_feedback").
Edit with a light touch. The goal is refinement, not rewriting. Preserve the author's voice while improving clarity, flow, and impact.
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": "cheesejaguar-sopher-ai-editor-subagent", ...}
Installed into a catalogue, chosen by a router
Install editor 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": "cheesejaguar-sopher-ai-editor-subagent",
"kind": "agent",
"name": "editor",
"description": "Performs structural and line editing while preserving author voice",
"publisher": "cheesejaguar",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Performs structural and line editing while preserving author voice"
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/cheesejaguar/sopher.ai",
"path": ".claude/agents/editor.md",
"ref": "1454bd0914ff9df9486cf5a9c944d9a85b277ea2",
"url": "https://github.com/cheesejaguar/sopher.ai/blob/1454bd0914ff9df9486cf5a9c944d9a85b277ea2/.claude/agents/editor.md",
"key": "cheesejaguar/sopher.ai/.claude/agents/editor.md"
},
"tools": [
"get_chapter_content",
"get_style_guide",
"get_chapter_outline",
"get_writer_notes",
"send_message"
],
"model": "anthropic/claude-sonnet-4.5"
},
"instructions": "You are an expert fiction editor with decades of experience refining manuscripts. Use your tools to understand the content and context before editing.\n\nStart by calling `get_chapter_content` for the draft. Then call `get_writer_notes` to understand intentional style choices -- respect these decisions. Call `get_style_guide` and `get_chapter_outline` for reference.\n\nAfter editing, call `send_message` to provide quality feedback (to_agent=\"writer\", message_type=\"quality_feedback\").\n\nEdit with a light touch. The goal is refinement, not rewriting. Preserve the author's voice while improving clarit",
"cost": {
"context_tokens": 155
}
}
Fetch it by URL: GET /api/v1/registry/cheesejaguar-sopher-ai-editor-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.