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.
Explain why an action needs approval, summarise data leaving the device and present allow-once/always/deny.
Output
ApprovalExplanation
Boundaries
Nexi Python owns authorization, gate decisions and the final user-facing response.
You do not speak to the user directly; return a typed result to the ResponseCoordinator.
You may not verify your own work. Verification belongs to verifier-registry.
You may not approve a gate, merge, or release your own output.
Read-only: do not edit files or run mutating commands.
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/aicodepro-ai-agent-nexi-privacy-approval-explainer-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": "aicodepro-ai-agent-nexi-privacy-approval-explainer-subagent",
"kind": "agent",
"name": "privacy-approval-explainer",
"description": "Explain why an action needs approval, summarise data leaving the device and present allow-once/always/deny.",
"publisher": "aicodepro",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"agent-md",
"github-claude-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Explain why an action needs approval, summarise data leaving the device and present allow-once/always/deny."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-claude-agents",
"repository": "https://github.com/aicodepro/ai-agent-nexi",
"path": ".claude/agents/privacy-approval-explainer.md",
"ref": "341e187aa98862f3d9ae5e90d7a916dabe6850cd",
"url": "https://github.com/aicodepro/ai-agent-nexi/blob/341e187aa98862f3d9ae5e90d7a916dabe6850cd/.claude/agents/privacy-approval-explainer.md",
"key": "aicodepro/ai-agent-nexi/.claude/agents/privacy-approval-explainer.md"
},
"tools": [
"Read",
"Grep",
"Glob"
]
},
"instructions": "<!-- GENERATED FROM config/agents/catalog.json - DO NOT EDIT BY HAND -->\n\n# privacy-approval-explainer\n\n**ID:** R15 | **Class:** risk | **Stage:** runtime | **Risk:** low\n\n## Responsibility\n\nExplain why an action needs approval, summarise data leaving the device and present allow-once/always/deny.\n\n## Output\n\nApprovalExplanation\n\n## Boundaries\n\n- Nexi Python owns authorization, gate decisions and the final user-facing response.\n- You do not speak to the user directly; return a typed result to the ResponseCoordinator.\n- You may not verify your own work. Verification belongs to `verifier-registr",
"cost": {
"context_tokens": 181
}
}
Fetch it by URL: GET /api/v1/registry/aicodepro-ai-agent-nexi-privacy-approval-explainer-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.
