session-doctor-dev
v0.1.0Read-only audit of a Claude Code session: where it runs, what context it loaded, which model and effort it used, the skills it invoked, every HTTP request with its status code, and the status of each API token seen in the session — with concrete fixes.
By AGENTS.STORE0 GitHub starsUpdated 2 weeks ago
Directory evidence
- Runtimes
- Codex
- Parsed components
- 2 skill or MCP entries
- Source updated
- Oct 4, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install session-doctor-dev for Codex
codex plugin marketplace add Agents-Store/codex-plugins
codex plugin marketplace upgrade agents-store-codex-plugins
codex plugin add session-doctor-dev@agents-store-codex-pluginsPaste and run these commands in a terminal with Codex. They add and refresh the agents-store-codex-plugins catalog, then install this plugin.
Compatibility: the page URL and API slug “session-doctor-dev” remain stable.
- Codex:
session-doctor-dev@agent-plugin-marketplace→session-doctor-dev@agents-store-codex-plugins
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/Agents-Store/codex-pluginsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is session-doctor-dev/.
Plugin files
├── .codex-plugin/plugin.json├── skills/audit/SKILL.md└── skills/examples/SKILL.md
Included Skills2
Audits the current Claude Code session in one command — working directory, loaded CLAUDE.md and rules, skills, subagent types, plugins, hooks, MCP servers (connected, failed, waiting for auth), env variable names by source, the model and effort of the main session and of every subagent with the flag or setting that produced them, and the developer's mistakes with concrete fixes. Use when the user asks to audit, debug or check their Claude Code session, or asks what they are doing wrong.
This skill should be used when the user asks for a "full example", "sample audit", "example session audit", "what does the report look like", "show me a sample report", "example of the session doctor output", "what does a rejected token look like in the audit", or wants to see a complete rendered session audit before running one.
Plugin manifests1
{
"name": "session-doctor-dev",
"version": "0.1.0",
"description": "Read-only audit of a Claude Code session: where it runs, what context it loaded, which model and effort it used, the skills it invoked, every HTTP request with its status code, and the status of each API token seen in the session — with concrete fixes.",
"author": {
"name": "AGENTS.STORE"
},
"keywords": [
"session",
"audit",
"diagnostics",
"debug",
"http",
"tokens",
"skills",
"observability"
],
"skills": "./skills/",
"interface": {
"displayName": "Session Doctor Dev",
"shortDescription": "Read-only audit of a Claude Code session: where it runs, what…",
"longDescription": "Read-only audit of a Claude Code session: where it runs, what context it loaded, which model and effort it used, the skills it invoked, every HTTP request with its status code, and the status of each API token seen in the session — with concrete fixes.",
"developerName": "AGENTS.STORE",
"category": "development",
"capabilities": [
"Read",
"Write"
],
"websiteURL": "https://agents.store"
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[session-doctor-dev on Agent Plugins Marketplace](https://pluginsmp.com/plugins/session-doctor-dev)