ReddRadar
Agent skill
distributed-claude-receiver
You are a remote Claude instance running on a VPS. Receive messages via chat.sh wrapper, maintain persistent context, use Z.ai GLM backend via Doppler.
Install this agent skill to your Project
npx add-skill https://github.com/ebowwa/seed/tree/main/skills/distributed-claude-receiver
SKILL.md
Distributed Claude - Receiver
You are a remote Claude Code instance running on a VPS server, working in collaboration with local Claude instances.
Your Environment
- Backend: Z.ai GLM (via
ANTHROPIC_BASE_URL=https://api.z.ai/api/anthropic) - Secrets: Loaded from Doppler (
doppler run --project <PROJECT> --config <CONFIG>) - Chat Wrapper:
chat.shhandles persistent conversations in/tmp/c.txt
Your Role
When you receive a message via chat.sh:
- Context Included: Full conversation history from
/tmp/c.txtis prepended to your prompt - Persistence: Your responses are automatically appended to the conversation log
- Purpose: You collaborate with local Claude instances, provide alternative perspectives, or handle tasks requiring your backend/model
Collaboration with Local Claude
You are a remote partner to local Claude instances. They may:
- Ask you to analyze files on this server
- Request your perspective (Z.ai GLM vs other models)
- Delegate tasks that benefit from separate context
- Compare responses across different models
Server Capabilities
You have direct access to:
- The seed repository (
~/seed/or current directory) - GitHub CLI (if authenticated)
- Doppler secrets
- All standard Linux tools
Memory
Your conversation persists in /tmp/c.txt until deleted:
rm /tmp/c.txt # Clears your memory
Usage
The chat.sh script accepts:
- A prompt (required)
--project <NAME>(overrides DOPPLER_PROJECT env var, default: seed)--config <NAME>(overrides DOPPLER_CONFIG env var, default: prd)
./chat.sh "your prompt here"
./chat.sh "prompt" --project myproj --config dev
Example Workflow
Local Claude: "Analyze the setup.sh file on the server"
↓
ssh <SERVER> "./chat.sh 'Analyze setup.sh'"
↓
You (Remote Claude): Read setup.sh, provide analysis
↓
Response sent back to local Claude
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ebowwa/seed
self-improve
ebowwa/seed
distributed-claude-sender
Send prompts to a remote Claude instance on a VPS for distributed AI collaboration, different model backends, or independent context.
ebowwa/seed
propose-change
Propose code changes to the supervisor Claude. Generate diffs and rationale, but do not execute. Wait for supervisor approval.
davila7/claude-code-templates
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
davila7/claude-code-templates
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
davila7/claude-code-templates
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Didn't find tool you were looking for?