Soul Guardian

A filesystem integrity monitor for your agent's core configuration files. It watches SOUL.md, AGENTS.md, and other workspace files for unauthorized changes, auto-restores critical ones to their approved baseline, and generates security alerts you can wire into your heartbeat workflow. The audit log is hash-chained for tamper evidence, and it refuses to touch symlinks. Useful if you're running long-lived agents and want to catch prompt injection attempts or accidental overwrites before they cause problems. The alerting output is designed to be relayed directly to users, so you can integrate it without writing parsing logic. Requires Python 3 and assumes you're okay with automatic file restoration on drift.

skills.sh installs: 257
GitHub stars: 1.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add prompt-security/clawsec --skill soul-guardian --agent claude-code

Installs into .claude/skills of the current project.

Files

soul-guardian 👻

Protects your agent's core files (SOUL.md, AGENTS.md, etc.) from unauthorized changes with automatic detection, restoration, and user alerting.

Vercel Skills Installation

Install with the Vercel Skills CLI for this harness:

npx skills add prompt-security/clawsec --skill soul-guardian -a openclaw -y

Operational Notes

Required runtime: python3
Optional runtime: openclaw for cron integration, launchctl for macOS scheduling, bash for the demo helper
Side effects: can auto-restore protected files to their approved baseline and writes audit/quarantine state locally
Network behavior: none by default
Trust model: any scheduling is opt-in, but restore mode intentionally overwrites drifted files

Release Artifact Verification

For standalone installs, verify the signed release manifest before trusting SKILL.md, skill.json, or the archive. The skill.json file is the package metadata/SBOM source, and the release pipeline signs checksums.json with the ClawSec release key.