Self Driving Verify — Security skill for Claude Code
Verify a Self-Driving Portfolio run's contracts, hashes, and audit chain.
How to install Self Driving Verify
Installs to ~/.claude/skills/nutdnuy-self-driving-portfolio-skill-self-driving-verify/SKILL.md
mkdir -p ~/.claude/skills/nutdnuy-self-driving-portfolio-skill-self-driving-verify && curl -fsSL https://raw.githubusercontent.com/nutdnuy/self-driving-portfolio-skill/HEAD/commands/self-driving-verify.md -o ~/.claude/skills/nutdnuy-self-driving-portfolio-skill-self-driving-verify/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Self Driving Verify does
description: Verify a Self-Driving Portfolio run's contracts, hashes, and audit chain argument-hint: "" allowed-tools: Bash(cd:*), Bash(python:*), Bash(python3:*)
Verify an existing governed run before interpreting it. Resolve the run folder to an absolute path before changing directories.
Run:
cd "${CLAUDE_PLUGIN_ROOT}" && python3 pipeline/verify.py ""
Report `ok`, status, artifact count, event count, and audit head. Treat any failure as
Alternatives in Security
- ThinkWatch — Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII 817 ★
- Review Artifact — Creates one polished, self-contained HTML artifact from review findings, audit notes, PR feedback, code review 652 ★
- Maestro Odyssey — Long-running iterative cycle — one entry, seven modes (debug improve planex review security defensive ui) 530 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Threat Report Killchain
Claude skill to convert CTI reports into cyber kill chain, Diamond Model views and create a TTP-to-ATT&CK/ATLA
Cc User Autopsy
Honest, evidence-traceable peer-review skill for Claude Code users. Rule-based 8-dim scoring + LLM peer review
Portfolio Audit Output
Audit generated portfolio optimization weights and report
Executive Summary Findings
Build a portfolio security summary from current findings, risk, remediation, and audit coverage.
Migrate Audit
Read-only executive audit — costed effort, risks, recommended target; multiple apps → portfolio synthesis
Audit Automations
Audit the automation portfolio and sequence the work by expected value
Related Agents
Code Audit GitHub Workflows
Audits GitHub Actions workflow YAML and composite-action YAML for supply-chain, injection, permission, and sec
Demo Validator Web
Browser-driving validator for the live-demo and workbench builds — uses the Playwright MCP server (configured
Graph Builder
Aegis Ticket Graph BUILDER node — turns evidence into a plan.v1 change package with radius/undo/verify per ste