
Security
Two agent security workflow that's more focused than general code review. Aegis does the vulnerability scan checking for injection attacks, auth issues, hardcoded secrets, and OWASP Top 10 patterns, then arbiter verifies your fixes and runs security tests. Good for authentication code, payment processing, or before deploying anything that touches user data. The severity tagging (critical/high/medium/low) with file locations makes triage straightforward. Includes dependency scanning and has flags for narrowing scope to just secrets or packages. Honestly feels like what you'd want between regular reviews and a full pentest, especially if you're working solo without a dedicated security person.
- skills.sh installs
- 532
- GitHub stars
- 3.9K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add parcadei/continuous-claude-v3 --skill security --agent claude-codeInstalls into .claude/skills of the current project.
Files
/security - Security Audit Workflow
Dedicated security analysis for sensitive code.
When to Use
- "Security audit"
- "Check for vulnerabilities"
- "Is this secure?"
- "Review authentication code"
- "Check for injection attacks"
- Before handling auth, payments, user data
- After adding security-sensitive features
Workflow Overview
┌─────────┐ ┌───────────┐
│ aegis │───▶│ arbiter │
│ │ │ │
└─────────┘ └───────────┘
Security Verify
audit fixes
Agent Sequence
| # | Agent | Role | Output |
|---|---|---|---|
| 1 | aegis | Comprehensive security scan | Vulnerability report |
| 2 | arbiter | Verify fixes, run security tests | Verification report |
Why Dedicated Security?
The /review workflow focuses on code quality. Security needs:
- Specialized vulnerability patterns
- Dependency scanning
- Secret detection
- OWASP Top 10 checks
- Authentication/authorization review
Execution
Phase 1: Security Audit
Task(
subagent_type="aegis",
prompt="""
Security audit: [SCOPE]
Scan for:
Sponsors
Details
- Repository
- github.com/parcadei/continuous-claude-v3
- Categories
- Security, Automation & Workflows
- First seen
- Jun 3, 2026
More from parcadei/continuous-claude-v3
All 108- Research Agent530
- Perplexity Search528
- Agent Orchestration525
- Ast Grep Find523
- Git Commits523
- Remember523
- Repo Research Analyst522
- Review521
- Planning Agent520
- Repoprompt517
- Agent Context Isolation514
- Parallel Agents514
- Create Handoff512
- Continuity Ledger511
- Debug509
- Hooks509
- Prove508
- Compound Learnings507
- Hook Developer506
- Tldr Code506
- Commit503
- Research External503
- Test503
- Background Agent Pings502