Verify Catalog — AI skill for Claude Code
Check the model catalog code against the installed Codex CLI.
How to install Verify Catalog
Installs to ~/.claude/commands/parisbs-codex-subagent-mcp-verify-catalog.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/parisbs/codex-subagent-mcp/HEAD/.claude/commands/verify-catalog.md -o ~/.claude/commands/parisbs-codex-subagent-mcp-verify-catalog.md Restart Claude Code, or start a new session, for it to be picked up.
What Verify Catalog does
description: Check the model catalog code against the installed Codex CLI allowed-tools: Bash(codex debug models), Bash(codex --version), Bash(npm test), Read, Grep
The Codex model catalog changes when OpenAI ships new models. Confirm this repository still describes reality.
- Run
codex --versionandcodex debug models | jq -r '.models[] | select(.visibility=="list") | "\(.slug) default=\(.default_reasoning_level) efforts=[\([.supported_reasoning_levels[].effort] | join(","))]"'.
Alternatives in AI
- Lumenx Model Onboarding — LumenX 模型接入与文档更新流程 - 厂商文档抓取、model_catalog 更新、运行时范围判断、端到端验证 1.2k ★
- Agentlint — Local guardrails for AI coding agents 38 ★
- Claude Skill Citation Checker — AI citation hallucination detector — verify .bib files against CrossRef, Semantic Scholar, OpenAlex 29 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Update OpenAI Models
Verify Netclaw's OpenAI Codex live model catalog query when OpenAI or Codex changes model discovery behavior.
AI Agent OS
Local-first dashboard for running a team of AI agents - connect ChatGPT, Claude, Grok, Cursor, Hermes or any O
Agent Belt
Reproducible evaluation for AI coding agents. Multi-turn scenarios against Claude Code, Codex, Copilot, Cursor
Model Check
Validate Claude model usage against current public models
Pbi Help
Display the complete PBI skill command reference with version check, organized by category (paste-in, PBIP, wo
Vibeos
AI-native Linux: Ubuntu 24.04 LTS, KDE Plasma, a local Ollama model and an agent CLI, installed in about 10 mi
Related Agents
Codex Exec Writer
Explicit workspace-writing one-shot execution through the installed Codex CLI
Skill Updater
Use this agent to automatically check for and apply skill, agent, and hook updates from the cognitive-core fra
Arthur
Independent code review via the Codex CLI (read-only, headless) for a second opinion that reads project files