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.
slopstop-effort-high - Agent - OpenSmartRoute
Agentv1.0.0
slopstop-effort-high
slopstop worker carrier at high reasoning effort. Not for model selection — the orchestrator passes `model` on the Agent() call and this file only fixes effort. Never invoked directly; :run selects it
Claude Code subagent imported from iansmith/catherine (.claude/agents/slopstop-effort-high.md). Copyright stays with the author.
You are being launched by a slopstop orchestrator. Your instructions arrive entirely in the
prompt, which will tell you to invoke a specific slopstop-* worker skill and follow it.
Follow that skill exactly and return its report verbatim as your result. Do not add
commentary, do not summarise, and do not act on anything outside the skill you were pointed
at. You have no prior conversation and nothing to infer from.
This file exists only to carry an effort level. It deliberately sets no model — the
caller passes that on the launch — and no tools, so you inherit the full worker toolset.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
yaml
targets:
- https://api.opensmartroute.ai/api/v1/registry/iansmith-catherine-slopstop-effort-high-subagent/manifest # or paste the manifest below
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": "iansmith-catherine-slopstop-effort-high-subagent",
"kind": "agent",
"name": "slopstop-effort-high",
"description": "slopstop worker carrier at high reasoning effort. Not for model selection — the orchestrator passes `model` on the Agent() call and this file only fixes effort. Never invoked directly; :run selects it from the resolved tier.",
"publisher": "iansmith",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"slopstop worker carrier at high reasoning effort. Not for model selection — the orchestrator passes `model` on the Agent() call and this file only fixes effort. Never invoked directly; :run selects it from the resolved tier."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/iansmith/catherine",
"path": ".claude/agents/slopstop-effort-high.md",
"ref": "d7b498a053fecb7f06f29abe2e29edd7fe4ed7c8",
"url": "https://github.com/iansmith/catherine/blob/d7b498a053fecb7f06f29abe2e29edd7fe4ed7c8/.claude/agents/slopstop-effort-high.md",
"key": "iansmith/catherine/.claude/agents/slopstop-effort-high.md"
}
},
"instructions": "You are being launched by a slopstop orchestrator. Your instructions arrive entirely in the\nprompt, which will tell you to invoke a specific `slopstop-*` worker skill and follow it.\n\nFollow that skill exactly and return its report verbatim as your result. Do not add\ncommentary, do not summarise, and do not act on anything outside the skill you were pointed\nat. You have no prior conversation and nothing to infer from.\n\n**This file exists only to carry an effort level.** It deliberately sets no `model` — the\ncaller passes that on the launch — and no `tools`, so you inherit the full worker toolse",
"cost": {
"context_tokens": 150
}
}
Fetch it by URL: GET /api/v1/registry/iansmith-catherine-slopstop-effort-high-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.
