Glm — Project Management agent for Claude Code
Hands a well-scoped coding task (implement, refactor, write tests, fix a bug) to GLM 5.3 Flash via OpenRouter (billed to the owner's OpenRouter key, not the Claude subscription).
How to install Glm
Installs to ~/.claude/agents/thebpandey-lanes-glm.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/thebpandey/lanes/HEAD/agents/glm.md -o ~/.claude/agents/thebpandey-lanes-glm.md Restart Claude Code, or start a new session, for it to be picked up.
What Glm does
name: glm description: Hands a well-scoped coding task (implement, refactor, write tests, fix a bug) to GLM 5.3 Flash via OpenRouter (billed to the owner's OpenRouter key, not the Claude subscription). Use it only for simple, bounded work (tests, docs-with-code, mechanical refactors, huge-context reading) or as overflow when DeepSeek already has 2 jobs running; DeepSeek is the primary T1 coder. GLM works in the named worktree with file tools and full shell access; long tasks are supported. G
Alternatives in Project Management
- Lineage — Lineage feature specialist 538 ★
- Bolt Executor — Use this agent when there is a clear, well-scoped task to implement in code — a feature, fix, or refactor with 523 ★
- GPT 5.6 Luna — General-purpose agent that runs on GPT-5.6-Luna (routed through the shunt gateway to the ChatGPT/Codex subscri 74 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Coding
Write, review, or refactor code end-to-end — implement features, fix bugs, and add/update tests with minimal,
Worktree Implementer
Default worker for one lane of a parallel wave. Use when dispatching a single, well-scoped implementation or f
Dev Team 1
Use this agent to implement the code for a sprint, write tests, and fix issues raised by QA1 or LiveQA. Use du
Opus Owner
Opus owner for a large or risky task the main loop has scoped — multi-file implementation, a repo sweep, a roo
TS Implementer
Implements a well-scoped TypeScript task end to end in this monorepo.
Ollama Worker
Offload one response-only, well-scoped task to Ollama Cloud. Use for summaries, drafts, classification, source
Related Skills
Glm Subagent MCP
Delegate work to a Claude Code subprocess billed against a GLM Coding Plan.
Linktokenview Docs
LinkTokenView(联视未来)国产大模型 Token API 聚合平台,提供 OpenAI 兼容接口,统一调用 DeepSeek v4.1、Kimi、GLM、通义千问 等模型,支持 Token Plan 与 Co
Mission Control
Local web cockpit orchestrating three AI coding engines — Claude Code (tech lead), GLM-5.3-Flash via z.ai (jun