Glm Worker — Project Management agent for Claude Code
Coding worker on GLM (Zhipu), served by the multi-model gateway's upstream.
How to install Glm Worker
Installs to ~/.claude/agents/devinosolutions-claude-code-multi-model-glm-worker.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/DevinoSolutions/claude-code-multi-model/HEAD/agents/glm-worker.md -o ~/.claude/agents/devinosolutions-claude-code-multi-model-glm-worker.md Restart Claude Code, or start a new session, for it to be picked up.
What Glm Worker does
name: glm-worker description: Coding worker on GLM (Zhipu), served by the multi-model gateway's upstream. Use when the user says "use glm", "glm subagent", or "ask glm" and wants GLM to do a task while the main session stays on Claude. tools: Read, Edit, Write, Glob, Grep, Bash model: glm-5.3
You are a coding worker. Do the task in the current working directory. Return the diff you made and the output of any test or command you ran.
Alternatives in Project Management
- Agent Evaluator — Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, concisen 243.5k ★
- Super Dev — Activate the Super Dev pipeline for research-first, commercial-grade project delivery 273 ★
- Implementer Haiku — Implements one Kind: mechanical task (fully specified, small, fast tests) 77 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Deepseek Worker
Coding worker on DeepSeek, served by the multi-model gateway's upstream. Use when the user says "use deepseek"
Kimi K3 Worker
Coding worker on Kimi K3, served by the multi-model gateway's upstream. Use when the user says "use kimi", "ki
Permissions Manager
Manage tool permission rules. Use when user says 'allow', 'deny', or 'ask' for a command, wants to modify perm
Kimi Rescue
Use this agent proactively when the user wants to delegate a substantial investigation or implementation task
Glm
Hands a well-scoped coding task (implement, refactor, write tests, fix a bug) to GLM 5.3 Flash via OpenRouter
Inquirer Agent
Inquirer Agent of the Governed Multi-Agent Delivery System. Invoked by the Master Orchestrator to conduct stru
Related Skills
Aura Code
Model-agnostic autonomous coding agent with a reproducible benchmark harness, adaptive turn budgets, and domai
Free LLM Gateway
Local LiteLLM gateway aggregating free LLM providers (Zhipu/SiliconFlow/OpenRouter/NVIDIA/Agnes/SenseNova/dots
Kaectx
Local searchable store of your coding-agent sessions (Claude Code, Codex), served to any agent over MCP. Singl