docs: reorganize agent-auth around canonical docs#19
Closed
saif-at-scalekit wants to merge 5 commits into
Closed
Conversation
Shift the agent-auth plugin toward a Tessl-like docs/skills/rules layout so durable AgentKit guidance is separated from Claude-specific runtime files. This makes live metadata the documented source of truth for tools while keeping existing connector notes available as secondary references. Co-authored-by: Cursor <cursoragent@cursor.com>
Raise the agent-auth plugin manifest to 2.0.0 so the hybrid AgentKit reorganization can ship as a major update and users can pick up the new version cleanly. Co-authored-by: Cursor <cursoragent@cursor.com>
Add a one-line Claude Code installer that adds the marketplace, installs the agent-auth plugin, and points users to enable auto-update. Also thread official docs.scalekit.com AgentKit links through the new canonical docs so the plugin can point back to the published product documentation. Co-authored-by: Cursor <cursoragent@cursor.com>
Add the stable llms.txt and sitemap-0.xml links to the main Claude Code auth stack docs and the canonical agent-auth docs entrypoints so users and agents have clear fallback indexes into published Scalekit documentation. Co-authored-by: Cursor <cursoragent@cursor.com>
Move the live AgentKit discovery and execution workflow into the testing skill so the plugin follows the modern skills-first structure. Keep `/test-tool` only as a legacy compatibility alias to preserve older usage without making `commands/` the source of truth. Co-authored-by: Cursor <cursoragent@cursor.com>
ravibits
reviewed
May 6, 2026
| allowed-tools: Bash | ||
| --- | ||
|
|
||
| # Legacy AgentKit Tool Tester |
There was a problem hiding this comment.
Why do we need this legacy tools thing?
| # Tool Discovery | ||
|
|
||
| > Canonical doc: [../docs/tool-discovery.md](../docs/tool-discovery.md) | ||
|
|
There was a problem hiding this comment.
I went through this doc and I am not sure if the entire contents are correct and valid;
@saif-at-scalekit Did you review the agent generated contents thoroughly?
58 tasks
Collaborator
Author
|
Superseded by #20 which incorporates this work and completes the full 5→2 plugin restructure (AgentKit + SaaSKit). |
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
4 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.
Summary
plugins/agent-autharound a canonicaldocs/,skills/, andrules/content model while keeping Claude-specific runtime files as adapter surfaces/test-toolplayground command/scriptreferences/content as secondary/canonical-pointer docs so live metadata is documented as the source of truth for tools and schemasTest plan
python3 -m py_compile skills/testing-agentkit-tools/scripts/connect.pyMade with Cursor