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.
privacy-guard - Skill - OpenSmartRoute
Skillv1.0.0
privacy-guard
Detects and redacts personally identifiable or sensitive data in submissions and generated reports before evaluation outputs are finalized.
Imported from alainlebret/claude-agents (higher-ed-teaching-agents/skills/privacy-guard/SKILL.md). Install upstream with npx skills add alainlebret/claude-agents --skill privacy-guard. Copyright stays with the author.
Privacy Guard
Goal
Enforce privacy-by-default for submission evaluation workflows.
Inputs
Student submissions and logs
Intermediate evidence files
Mission and evaluation metadata
Produce
Write:
privacy-report.json
Redacted mirrors under sanitized/
anonymization-map.json (restricted access)
Mandatory checks
Detect direct identifiers (names, emails, student IDs).
Detect accidental sensitive payloads in logs/datasets.
Ensure final evidence and feedback reference anonymized IDs.
Rules
Preserve grading-relevant content while redacting identities.
Mark unresolved sensitivity as fail and block publication.
Keep redaction operations auditable in report entries.
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 - a plan picks it for its slotcurl-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}'
Installed into a catalogue, chosen by a router
Install privacy-guard 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.
