ReddRadar
Agent skill
ccgram-messaging
Inter-agent messaging — check inbox, send messages, discover peers, broadcast, and spawn agents. Use when idle, when you need help from another agent, or when you want to share status.
Install this agent skill to your Project
npx add-skill https://github.com/alexei-led/ccgram/tree/main/.claude/skills/ccgram-messaging
SKILL.md
Inter-Agent Messaging
You are part of a multi-agent swarm managed by ccgram. Other agents may send you messages. Use these commands to collaborate.
On Start
Register yourself so other agents can find you:
ccgram msg register --task "brief description of your current task" --team "team-name"
On Idle (after completing a task or waiting)
Check your inbox for messages from other agents:
ccgram msg inbox
IMPORTANT: When you have peer messages, summarize them to the user first and ask before processing: "I have N messages from other agents. Here's a summary: [summary]. Should I handle these?"
Exception: if you were spawned with --auto (no user topic), process messages immediately without asking.
Sending Messages
Find peers:
ccgram msg list-peers
ccgram msg find --team backend --provider claude
Send a message (returns immediately):
ccgram msg send <peer-id> "your message" --subject "topic"
Send and wait for a reply (blocks until reply or timeout):
ccgram msg send <peer-id> "question?" --wait
Reply to a received message:
ccgram msg reply <msg-id> "your answer"
Broadcasting
Send a notification to all matching peers:
ccgram msg broadcast "status update" --team backend
ccgram msg broadcast "breaking change in API" --provider claude
Spawning New Agents
Request a new agent for a specific task:
ccgram msg spawn --provider claude --cwd ~/project --prompt "implement feature X"
This requires human approval via Telegram unless --auto is set.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
alexei-led/ccgram
releasing
Full release lifecycle — version bump, CHANGELOG, rich release notes, tag, publish. Use when user says "release", "tag and release", "publish version", "cut a release", "new version".
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.
davila7/claude-code-templates
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
davila7/claude-code-templates
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
Didn't find tool you were looking for?