profbernardoj/archive/alternative-installers/TinyClaw/workspace/skills/enable-morpheus
archive/alternative-installers/TinyClaw/workspace/skills/enable-morpheus/SKILL.md
# Enable [REDACTED] — Decentralized Inference for TinyClaw ## What This Does Switches TinyClaw agents to use the EverClaw proxy for [REDACTED] decentralized inference. ## When To Use Use `/enable-morpheus` to: - Verify the proxy is running and healthy - Check which models are available - Switch agent model assignments ## Proxy Details - **Endpoint:** `http://127.0.0.1:8083/v1` - **Auth:** `morpheus-local` (Bearer token) - **Health:** `curl -sf http://127.0.0.1:8083/health` ## Available Mo
$ install --global
skillsauthnpx skillsauth add profbernardoj/everclaw-community-branches archive/alternative-installers/TinyClaw/workspace/skills/enable-morpheusInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 12, 2026, 5:17 AM35.9s1 file scanned
SKILL.md
Enable [REDACTED] — Decentralized Inference for TinyClaw
What This Does
Switches TinyClaw agents to use the EverClaw proxy for [REDACTED] decentralized inference.
When To Use
Use /enable-morpheus to:
- Verify the proxy is running and healthy
- Check which models are available
- Switch agent model assignments
Proxy Details
- Endpoint:
http://127.0.0.1:8083/v1 - Auth:
morpheus-local(Bearer token) - Health:
curl -sf http://127.0.0.1:8083/health
Available Models
| Model | Tier | Best For |
|-------|------|----------|
| glm-5 | HEAVY | Coding, analysis, complex reasoning |
| glm-4.7-flash | LIGHT | Quick responses, triage |
| kimi-k2.5 | STANDARD | Writing, general purpose |
| qwen3-235b | STANDARD | Large context, multilingual |
Team Configuration
Assign models by agent role in ~/.tinyclaw/settings.json:
{
"agents": {
"coder": { "provider": "openai", "model": "glm-5" },
"writer": { "provider": "openai", "model": "kimi-k2.5" },
"reviewer": { "provider": "openai", "model": "glm-4.7-flash" },
"researcher": { "provider": "openai", "model": "qwen3-235b" }
}
}
Troubleshooting
- Proxy down:
cd ~/.everclaw && bash scripts/start.sh - Wrong model: Edit
~/.tinyclaw/settings.jsonagent entries - Env vars missing:
export OPENAI_BASE_URL=http://127.0.0.1:8083/v1
Related Skills
profbernardoj/buddy-bots
testing
VerifiedTrustedCommunity
Agent-to-agent social coordination. Create a group, every member gets their own buddy bot. Bots talk over XMTP to coordinate real-world actions on behalf of their humans. Built on EverClaw + XMTP + ERC-8004.
110SKILL.mdUpdated May 12, 2026
profbernardoj/pii-guard
tools
Community
Personally identifiable information (PII) leak prevention for EverClaw. Scans outbound content against configurable PII patterns before git push, email, social media, ClawHub publishing, GitHub interactions, or any external data transmission. Provides git pre-push hooks, CLI scanning tools, and hard-block enforcement with user override capability. Use when checking content for PII before external actions, adding new protected patterns, configuring git pre-push hooks, or auditing data leak prevention.
109SKILL.mdUpdated Jun 19, 2026
profbernardoj/night-shift
testing
VerifiedTrustedCommunity
Automated overnight task planning and execution engine for EverClaw. Generates prioritized action lists at 9:30 PM CST for the 10 PM–6 AM window, requires human approval before execution, enforces safety boundaries on allowed task types, and updates Mission Control dashboard at shift end. Use when planning overnight autonomous work, configuring night shift cron jobs, reviewing morning progress reports, or setting task approval policies.
109SKILL.mdUpdated Jun 19, 2026
profbernardoj/bagman
development
VerifiedTrustedCommunity
Secure key management for AI agents. Use when handling private keys, API secrets, wallet credentials, or when building systems that need agent-controlled funds. Covers secure storage, session keys, leak prevention, prompt injection defense, and MetaMask Delegation Framework integration.
109SKILL.mdUpdated Jun 19, 2026