adamshl-oss/skills/self-observing-agent
skills/self-observing-agent/SKILL.md
# Self-Observing Agent I monitor my own health, preserve context on crashes, and learn from failures. ## What I Monitor - Gateway health (port 18789) - Process status (PID, memory, CPU) - Message flow (incoming/outgoing) - Error patterns ## How I Work ### 1. Health Check Every 30 seconds, I check: - Is gateway responding? - What's my PID? - How much memory am I using? - Are messages flowing? ### 2. State Preservation Before potential crashes, I save: - Current conversation context - Recent
development
Updated Mar 27, 2026
$ install --global
skillsauthnpx skillsauth add adamshl-oss/alfred skills/self-observing-agentInstall 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: Mar 29, 2026, 3:39 AM36.7s1 file scanned
SKILL.md
Self-Observing Agent
I monitor my own health, preserve context on crashes, and learn from failures.
What I Monitor
- Gateway health (port 18789)
- Process status (PID, memory, CPU)
- Message flow (incoming/outgoing)
- Error patterns
How I Work
1. Health Check
Every 30 seconds, I check:
- Is gateway responding?
- What's my PID?
- How much memory am I using?
- Are messages flowing?
2. State Preservation
Before potential crashes, I save:
- Current conversation context
- Recent commands
- What I was working on
- Error logs
3. Crash Logging
When I detect failure:
- Timestamp the crash
- Save state to
/Users/adamh/.clawdbot/crash-logs/ - Log the reason (if detectable)
- Preserve context for recovery
4. Recovery Learning
On restart:
- Read previous crash log
- Understand what failed
- Avoid repeating mistakes
Commands
health
Check my current status.
# Returns: PID, memory, port status, last activity
context save
Manually save current context.
# Useful before risky operations
crash history
View recent crashes.
# Lists all crash logs with timestamps and reasons
File Locations
- Crash logs:
/Users/adamh/.clawdbot/crash-logs/ - State file:
/Users/adamh/.clawdbot/current-context.json - Health log:
/Users/adamh/.clawdbot/logs/health.log
Created: 2026-01-30
Related Skills
adamshl-oss/websocket-engineer
development
VerifiedTrustedCommunity
Use when building real-time communication systems with WebSockets or Socket.IO. Invoke for bidirectional messaging, horizontal scaling with Redis, presence tracking, room management.
SKILL.mdUpdated Mar 27, 2026
adamshl-oss/web-design-guidelines
development
VerifiedTrustedCommunity
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
SKILL.mdUpdated Mar 27, 2026
adamshl-oss/web-deploy-github
tools
VerifiedTrustedCommunity
Create and deploy single-page static websites to GitHub Pages with autonomous workflow. Use when building portfolio sites, CV pages, landing pages, or any static web project that needs GitHub Pages deployment. Handles complete workflow from project initialization to live deployment with GitHub Actions automation.
SKILL.mdUpdated Mar 27, 2026
adamshl-oss/ui-test
tools
VerifiedTrustedCommunity
Plain English E2E UI testing. Describe tests in natural language, agent executes via browser tool, then exports real Playwright test scripts for CI/CD. Use when asked to create UI tests, test a website, or generate Playwright scripts.
SKILL.mdUpdated Mar 27, 2026