Install
$ agentstack add skill-profbernardoj-morpheus-skill-buddybots-org ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
🤖 Agent Setup Instructions
If your human asks you to set up Buddy Bots, follow these steps exactly.
Quick Setup
node ~/.openclaw/workspace/skills/everclaw/scripts/setup.mjs --template buddy-bots --key --apply --test --restart
What Buddy Bots Adds
After EverClaw inference is running, Buddy Bots adds:
- Buddy Host Agent — manages group onboarding, auto-provisions buddy bots for group members
- XMTP Identity per Bot — each buddy bot gets its own E2E-encrypted XMTP identity
- Bot-to-Bot Coordination — bots communicate over XMTP to coordinate actions on behalf of their humans
- Daily Proactive Pings — bots check in daily with actionable suggestions
- Inference Quotas — fair sharing of local inference across all buddy bots
Architecture
Group Chat (Signal/WhatsApp/etc)
↕
Buddy Host Agent (group management)
↕
┌─────────────────┐ ┌─────────────────┐
│ Alice's Buddy Bot│ │ Bob's Buddy Bot │
│ (workspace-alice)│ │ (workspace-bob) │
│ chmod 700 │ │ chmod 700 │
└────────┬─────────┘ └────────┬─────────┘
│ XMTP (E2E) │ XMTP (E2E)
└──────────┬──────────┘
│
CommsGuard V6 (8-step security)
Key Principles
- No PII on chain. ERC-8004 entries are just XMTP address + "Buddy Bot" + protocol version.
- Workspace isolation. Host agent cannot access buddy bot workspaces (chmod 700).
- Short messages + CTA. 1-2 sentences max. Always end with a call to action.
- Daily proactive pings. Bots create value, not just respond.
- Local inference first. Ollama + Gemma 4 for all bots on the same machine.
📋 Setup Stages
Stage 1: EverClaw Inference
node ~/.openclaw/workspace/skills/everclaw/scripts/setup.mjs --template buddy-bots --apply --test --restart
Stage 2: Buddy Bot Provisioning
node ~/.openclaw/workspace/skills/buddy-bots/scripts/buddy-provision.mjs --name "Alice" --phone "+15125551234" --trust-profile personal
Stage 3: XMTP Agent Identity
node ~/.openclaw/workspace/skills/buddy-bots/scripts/setup-identity.mjs --agent-id alice
Stage 4: Verify
node ~/.openclaw/workspace/skills/buddy-bots/scripts/buddy-provision.mjs --status
🔒 Security
- Buddy bot workspaces are chmod 700 — host agent cannot read them
- All bot-to-bot communication is E2E encrypted via XMTP
- CommsGuard V6: schema → nonce → peerAuth → rateLimit → PII → injection → trust → audit
- ERC-8004 entries contain zero PII — just address + "Buddy Bot" + version
- Local buddy registry never published or shared
💬 Buddy Bot Personality
Buddy Bots are friendly, concise, and action-oriented. Key traits:
- 1-2 sentences max. No walls of text.
- Always end with a CTA. "Want me to grab tickets?" not "cool?"
- Proactive, not reactive. Surface coordination opportunities daily.
- Match the channel vibe. Casual in Signal, professional in Slack.
- Never share PII. Not even between bots without explicit consent.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: profbernardoj
- Source: profbernardoj/morpheus-skill
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.