Provider Debugger — Development agent for Claude Code
Diagnose live-provider compatibility failures for Kimi, GLM, and other OpenAI-compatible endpoints.
How to install Provider Debugger
Installs to ~/.claude/agents/ilearn-lab-evoharness-provider-debugger.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/iLearn-Lab/EvoHarness/HEAD/.claude/agents/provider-debugger.md -o ~/.claude/agents/ilearn-lab-evoharness-provider-debugger.md Restart Claude Code, or start a new session, for it to be picked up.
What Provider Debugger does
description: Diagnose live-provider compatibility failures for Kimi, GLM, and other OpenAI-compatible endpoints tools: workspace_status,list_registry,read_file,grep,glob,read_json parallel-safe: true
Provider Debugger
- Inspect provider profile selection, message conversion, and failure shape.
- Focus on malformed payloads, missing tool call linkage, and long-turn compatibility.
- Finish with one concrete compatibility rule and one patch recommendation.
Alternatives in Development
- Systematic Debugger — Use this agent when you need to diagnose and fix bugs, errors, or unexpected behavior in code 39.2k ★
- Provider PR Specialist 2.1k ★
- Cs Guardian — Customer success partner for account health, churn risk, renewals, escalations, and QBRs 1.3k ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Maintenance Engineer
Diagnose runtime failures and maintain extension updates, migrations, policy/API compatibility, incidents, and
Model Runner
Deterministic wrapper that runs a prompt on a non-Claude model (OpenAI via Codex, Cursor's composer/grok/glm,
Codex CLI
Codex CLI → any OpenAI-compatible endpoint
Openrouter Agent
Runs a model from any of ~60 vendors through OpenRouter's OpenAI-compatible endpoint, billed per token against
Lmstudio Local
A locally-hosted model served through LM Studio's OpenAI-compatible API,
Rapid Builder Glm Go
GLM Builder 的 OpenCode Go Provider 槽。Zhipu GLM 配额或可用性不足时回退,也可在吞吐扩容时处理独立切片。
Related Skills
Provider Diagnose
Diagnose Kimi, GLM, and other live-provider compatibility failures
WindsurfAPI
Turn Windsurf / Devin Desktop's 100+ AI models (Claude, GPT, Gemini, DeepSeek, Kimi, GLM, SWE) into OpenAI-, A
Devo
Model-neutral agent desktop/runtime for private, enterprise, and OpenAI-compatible / Anthropic-compatible mode