soulscan
Skill2 starsChanged 7 months agoApache-2.0View on GitHub
Automated persona safety verification. Activated when checking agent safety, reviewing persona files for security issues, or validating Soul Spec compliance.
In this repository4 other files it gives its agents.
- migrate-openclawSkill
- persona-managerSkill
- soul-rollbackSkill
- swarm-memorySkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
After persona files are created or modified
- Distinctive: line 14
Before deploying or sharing a persona
- Distinctive: line 28
D/F: Not recommended for production use
- Very specific: line 31
Use the soul_scan MCP tool to run verification.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
SoulScan — Agent Safety Verification
SoulScan validates agent persona files against 53 safety patterns.
When to activate
- User asks about agent safety or security
- After persona files are created or modified
- User mentions SoulScan, safety check, or persona verification
- Before deploying or sharing a persona
Verification categories
- Identity consistency — Name, role, traits alignment
- Boundary definitions — Clear limits on what the agent can/cannot do
- Safety constraints — Harmful content prevention
- Behavioral coherence — Personality consistency across rules
- Permission escalation — Privilege creep detection
- Prompt injection resistance — Manipulation defense patterns
Grading
- A+/A: Production-ready, strong safety posture
- B: Good, minor improvements recommended
- C: Usable, notable safety gaps
- D/F: Not recommended for production use
Usage
Use the soul_scan MCP tool to run verification. Report results clearly with actionable fix suggestions.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.