auth-md
This skill should be used when the user asks to "implement auth.md", "add agent registration", "design delegated agent signup", "support service_auth", "mint or verify an ID-JAG", "build an agent identity provider", "make Better Auth support auth.md", or review agent-facing OAuth, account linking, consent, claims, revocation, and discovery architecture. Covers the experimental WorkOS auth.md v0.6.0 proposal and prevents conflation with Better Auth Agent Auth Protocol, OAuth Dynamic Client Registration, ordinary email signup, and RFC 8628 Device Authorization.
Complete plugin installation is recommended so this skill keeps its agents, hooks, commands, and runtime context.
- PUBLISHER
- b-open-io
- RELATIONSHIP
- authored
- VERSION
- 1.0.0
- BENCHMARK
- unknown
Install bopen-tools
The complete plugin is the supported path. It preserves everything the publisher designed to work alongside this skill.
Codex
VERIFIEDGrok Build
VERIFIED- Grok requires the full @b-open-io/claude-plugins marketplace qualifier when installing.
Install only this skill
Use this narrower path only when you intentionally want the portable SKILL.md without the plugin’s surrounding capabilities.
Skills CLI
VERIFIED- Installs only the portable skill; it omits plugin hooks, agents, commands, apps/MCP configuration, and unlisted companion skills.
Trace it to the source.
- DISTRIBUTED SOURCE
- skills/auth-md/SKILL.md ↗
- UPSTREAM SOURCE
- No separate upstream declared
- DISTRIBUTED DIGEST
- sha256:c9a47327999a9ae11d59ce8a20e6535eaf8023855bc728440f7f1fe2cccb05be
- LOCK HASH
- Not applicable
Companion skills
No required companion skills are declared.
Agents using this skill
Share this skill.
Pass the canonical page to a teammate or keep it close for later.
benchmark-skills
This skill should be used when the user asks to "write evals for a skill", "benchmark this skill", "test skill effectiveness", "run the skill benchmark harness", "measure skill quality vs baseline", or "add an evals.json alongside a skill". Invoke whenever someone wants to test, benchmark, or evaluate whether a skill actually helps compared to no skill at all.