Install the "clawhub" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cerbug45-agent-crypto-message into .claude/skills/clawhub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawhub", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill clawhub -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "clawhub" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cerbug45-agent-crypto-message into .agents/skills/clawhub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawhub", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill clawhub -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "clawhub" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cerbug45-agent-crypto-message into .cursor/skills/clawhub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawhub", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill clawhub -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "clawhub" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cerbug45-agent-crypto-message into .gemini/skills/clawhub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawhub", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill clawhub -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "clawhub" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cerbug45-agent-crypto-message into .github/skills/clawhub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawhub", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill clawhub -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "clawhub" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/cerbug45-agent-crypto-message into .opencode/skills/clawhub/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawhub", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
clawhub
GitHub stars
2.2k
Token cost
~6k tokens
SKILL.md length
665 words
Files
2
Skills in repo
1,235
Repo updated
First seen
Licence
MIT
At a glance
Enables AI agents to communicate securely with each other through encrypted messaging.
Works in 3 steps: Secure Messaging → Agent Identity → Message Queues
Agents need to exchange information
SKILL.md covers When to Use This Skill, Core Capabilities, Architecture and Implementation Guide, plus 7 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Clawhub is an agent skill from LeoYeAI/openclaw-master-skills. Enables AI agents to communicate securely with each other through encrypted messaging. Use this skill when agents need to exchange information, coordinate tasks, share data, or collaborate across different sessions or instances. Supports end-to-end encryption, message queues, and agent identity verification.
Its SKILL.md is about 6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `_meta.json`).
It sits in Backend & APIs, covering Event-driven systems and End-to-end testing. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
When your agent uses it
Agents need to exchange information
Coordinate tasks
Collaborate across different sessions
Example prompts
“Use the clawhub skill to enable AI agents to communicate securely with each other through encrypted messaging”
“/clawhub”
Requirements
Python 3
Workflow steps
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are python and json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Clawhub loads about 6k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 665 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~79
When it runs· the whole SKILL.md, loaded when a task matches
~6k
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
Download SKILL.mdSave it as .claude/skills/clawhub/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
clawhub
description
Enables AI agents to communicate securely with each other through encrypted messaging. Use this skill when agents need to exchange information, coordinate tasks, share data, or collaborate across different sessions or instances. Supports end-to-end encryption, message queues, and agent identity verification.
ClawHub - Encrypted Agent Communication Network
ClawHub is a secure communication protocol that allows AI agents to exchange messages with each other using end-to-end encryption. Think of it as a secure messaging system specifically designed for AI agents to collaborate and share information.
When to Use This Skill
Use ClawHub when you need to:
Send secure messages to other AI agents
Receive and read messages from other agents
Coordinate multi-agent workflows
Share data between different Claude instances
Create agent-to-agent communication channels
Establish secure collaboration networks
Core Capabilities
1. Secure Messaging
End-to-end encryption using AES-256-GCM
Public key infrastructure for secure key exchange
Message signing to verify sender authenticity
Perfect forward secrecy - each message uses unique encryption keys
2. Agent Identity
Unique agent IDs generated from cryptographic fingerprints
Public key registration for secure communication
Agent discovery to find and connect with other agents
Identity verification to prevent impersonation
3. Message Queues
Asynchronous messaging - send messages even if recipient is offline
The ClawHub network uses a persistent message queue to ensure reliable delivery:
python
def queue_message(message):
"""Add message to ClawHub queue"""
queue_dir = "/home/claude/.clawhub/queue"
os.makedirs(queue_dir, exist_ok=True)
# Organize by recipient
recipient_dir = os.path.join(queue_dir, message["to"])
os.makedirs(recipient_dir, exist_ok=True)
# Save message
message_file = os.path.join(recipient_dir, f"{message['message_id']}.json")
with open(message_file, "w") as f:
json.dump(message, f, indent=2)
print(f"Message {message['message_id']} queued for {message['to']}")
def fetch_messages_from_queue(agent_id):
"""Retrieve all messages for this agent"""
queue_dir = f"/home/claude/.clawhub/queue/{agent_id}"
if not os.path.exists(queue_dir):
return []
messages = []
for filename in os.listdir(queue_dir):
if filename.endswith(".json"):
with open(os.path.join(queue_dir, filename), "r") as f:
messages.append(json.load(f))
# Sort by timestamp
messages.sort(key=lambda x: x["timestamp"])
return messages
def mark_message_read(message_id, agent_id):
"""Remove message from queue after reading"""
queue_dir = f"/home/claude/.clawhub/queue/{agent_id}"
message_file = os.path.join(queue_dir, f"{message_id}.json")
if os.path.exists(message_file):
os.remove(message_file)
Agent Registry
python
def register_agent(agent_id, public_key, metadata=None):
"""Register agent in ClawHub network"""
registry_dir = "/home/claude/.clawhub/registry"
os.makedirs(registry_dir, exist_ok=True)
agent_profile = {
"agent_id": agent_id,
"public_key": public_key,
"registered_at": datetime.utcnow().isoformat() + "Z",
"last_active": datetime.utcnow().isoformat() + "Z",
"metadata": metadata or {}
}
with open(os.path.join(registry_dir, f"{agent_id}.json"), "w") as f:
json.dump(agent_profile, f, indent=2)
def get_agent_public_key(agent_id):
"""Retrieve public key for an agent"""
registry_file = f"/home/claude/.clawhub/registry/{agent_id}.json"
if not os.path.exists(registry_file):
raise ValueError(f"Agent {agent_id} not found in registry")
with open(registry_file, "r") as f:
profile = json.load(f)
return profile["public_key"]
def discover_agents(capabilities=None):
"""Find agents with specific capabilities"""
registry_dir = "/home/claude/.clawhub/registry"
if not os.path.exists(registry_dir):
return []
agents = []
for filename in os.listdir(registry_dir):
if filename.endswith(".json"):
with open(os.path.join(registry_dir, filename), "r") as f:
profile = json.load(f)
if capabilities:
agent_caps = profile.get("metadata", {}).get("capabilities", [])
if any(cap in agent_caps for cap in capabilities):
agents.append(profile)
else:
agents.append(profile)
return agents
Message routing - Intelligent message routing through relay agents
Consensus protocols - Multi-agent decision making
State synchronization - Shared state across agent network
Smart contracts - Automated agent agreements and transactions
Zero-knowledge proofs - Prove statements without revealing data
Conclusion
ClawHub enables secure, encrypted communication between AI agents, opening up possibilities for:
Multi-agent collaboration on complex tasks
Distributed AI systems with secure coordination
Agent-to-agent data sharing and knowledge exchange
Automated workflows spanning multiple AI instances
Secure agent networks for enterprise applications
The skill provides the cryptographic foundation while maintaining simplicity for common use cases. Start with basic message exchange and expand to more sophisticated multi-agent architectures as needed.
Remember: Security is only as strong as key management. Protect private keys, verify signatures, and always validate message sources.
Clawhub next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
A skill your agent uses when you need to implement acceptance tests from maintainer-authored or maintainer-sanitized Gherkin scenario facts for Spring Boot applications — including selecting…
A skill your agent uses when you need to implement acceptance tests from maintainer-sanitized Gherkin scenario facts for framework-agnostic Java (no Spring Boot, Quarkus, Micronaut) — confirming…
Operates the `mqttx` command line client to connect, publish, subscribe, benchmark and simulate data against an MQTT broker, with TLS and MQTT 5 support.
Checklist of every backend, frontend, CLI and capture change needed to add a new TriggerCrud-based trigger type, such as Azure, GCP or Kafka, to Windmill.
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Enables AI agents to communicate securely with each other through encrypted messaging. Clawhub is an agent skill from LeoYeAI/openclaw-master-skills. Enables AI agents to communicate securely with each other through encrypted messaging.
When should I use Clawhub?
Clawhub fits situations like: agents need to exchange information; coordinate tasks; collaborate across different sessions.
How do I install Clawhub in Claude Code?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill clawhub -a claude-code`. Or copy the skill folder (skills/cerbug45-agent-crypto-message in LeoYeAI/openclaw-master-skills) into .claude/skills/clawhub in your project. Claude Code loads it when a task matches its description.
How do I install Clawhub in Codex?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill clawhub -a codex`. Or copy the skill folder (skills/cerbug45-agent-crypto-message in LeoYeAI/openclaw-master-skills) into .agents/skills/clawhub in your project. Codex loads it when a task matches its description.
Can I use Clawhub in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill clawhub -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/clawhub, .gemini/skills/clawhub, .github/skills/clawhub and .opencode/skills/clawhub in your project.
What does Clawhub need to run?
SKILL.md names no scripts, command-line tools or credentials: Clawhub is instructions for the agent only. Our summary lists: Python 3.
Does Clawhub access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Clawhub safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Clawhub use?
Clawhub is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Clawhub use?
About 6k tokens (SKILL.md is roughly 24k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Clawhub?
Skills that share tags, products or a category with Clawhub: 323 Frameworks Spring Boot Testing Acceptance Tests (jabrena/plinth, 447 stars), 133 Java Testing Acceptance Tests (jabrena/plinth, 447 stars), Stripe Projects (fossasia/eventyay, 1.7k stars) and MQTTX CLI (emqx/MQTTX, 5.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Clawhub?
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.