# subagentrubrics.com — the Rubric primitive

> A durable library of gradeable rubrics, generalized directly from Anthropic's real Managed Agents outcome/rubric schema (define-outcomes.md), each a markdown document of explicit, gradeable per-criterion scoring.

## API
- GET /api/rubrics — list all rubrics, filterable by ?rubric_type=text or ?rubric_type=file
- GET /api/rubrics/:id — fetch one rubric by id
- POST /api/rubrics — create a rubric (gated by RUBRICS_WRITE_SECRET)
- GET /api/changes — newest-first change feed (?cursor=&limit=) for polling agents
- POST /mcp — Streamable-HTTP MCP endpoint (initialize / tools/list / tools/call get_rubrics); server card at /.well-known/mcp/server-card.json

## Grounding
A rubric here is what define-outcomes.md defines: a markdown document of explicit, gradeable per-criterion scoring, referenced from a session's user.define_outcome event.
Canonical source: https://platform.claude.com/docs/en/managed-agents/define-outcomes.md

## Family
This site is one of the Cloudflare Workers in the subagent*.com family. For the
live, machine-readable directory of every sibling domain, Cloudflare zone ID,
and worker binding, fetch:
https://subagentsubdomains.com/api/dns-zones

For a unified catalog of every API route across every primitive in the family:
https://subagentapi.com/api/catalog