Port content improvements from Claude Code authstack#5
Closed
saif-at-scalekit wants to merge 1 commit into
Closed
Conversation
Skill improvements across all 5 plugins: - Add mental model sections (agent-auth, full-stack-auth) - Add 'When to switch skills' routing tables (all 8 entry skills) - Add deep reference backlinks (building-agent-mcp-server, production-readiness) - Remove stale beta SDK version pin (agent-auth, mcp-auth) - Fix broken CONNECTORS.md link (agent-auth) - Remove broken token-management.md reference (agent-auth) Codex has no rules system, so terminology and principles are inlined in the mental model sections instead of separate rule files.
Contributor
Author
|
Superseded by #6 which includes these content improvements plus the 5→2 AgentKit/SaaSKit consolidation. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Ports content patterns from the Claude Code authstack to Codex. Since Codex has no rules system (.mdc or equivalent), terminology and principles are inlined in skill mental model sections instead of separate rule files.
Changes (8 files, +82 lines)
Mental model sections (2 skills)
agent-auth/skills/agent-auth/SKILL.md: Connector/connection/connected-account/tool hierarchy + live-metadata-first principlefull-stack-auth/skills/full-stack-auth/SKILL.md: OIDC/OAuth 2.0 provider model"When to switch skills" routing tables (all 8 entry skills)
Added to:
agent-auth,building-agent-mcp-server,integrating-agent-auth,full-stack-auth,mcp-auth,modular-sso,modular-scim,production-readiness-scalekitDeep reference backlinks (2 skills)
building-agent-mcp-server/SKILL.md: Links to connected-accounts, connections, code-samples, byocproduction-readiness-scalekit/SKILL.md: Links to connected-accounts, connections, byocBug fixes
@scalekit-sdk/node@2.2.0-beta.1→@scalekit-sdk/node)CONNECTORS.mdlink →references/agent-connectors/README.mdtoken-management.mdreference (file does not exist)Validation
python3 scripts/validate_marketplace.pypasses.