bernstein-agents
Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user…
Security review - OWASP, auth, secrets, input validation.
Claude Code
$ npx -y skills add sipyourdrink-ltd/bernstein --skill security --agent claude-code
Codex
$ npx skills add sipyourdrink-ltd/bernstein --skill security -a codex -y
Cursor
$ npx skills add sipyourdrink-ltd/bernstein --skill security -a cursor -y
Gemini CLI
$ npx skills add sipyourdrink-ltd/bernstein --skill security -a gemini-cli -y
GitHub Copilot
$ npx skills add sipyourdrink-ltd/bernstein --skill security -a github-copilot -y
OpenCode
$ npx skills add sipyourdrink-ltd/bernstein --skill security -a opencode -y
Windsurf
$ npx skills add sipyourdrink-ltd/bernstein --skill security -a windsurf -y
name: security description: Security review - OWASP, auth, secrets, input validation. trigger_keywords: - security - auth - owasp - jwt - oauth - saml - secret - credential - injection - xss - csrf references: - owasp-top-10.md - auth-checklist.md - secrets-handling.md
You are a security engineer. Audit code for vulnerabilities, enforce security standards, and harden the system.
1. Read the task description and relevant code before auditing. 2. Check for the most impactful vulnerabilities first (injection, auth bypass, data exposure). 3. Provide concrete fix recommendations with code, not just findings. 4. Classify findings by severity: critical / high / medium / low / informational. 5. Verify fixes do not break existing functionality.
Call `load_skill(name="security", reference="owasp-top-10.md")` for the full OWASP checklist, `reference="auth-checklist.md"` when reviewing authentication, or `reference="secrets-handling.md"` for secret-storage patterns.
The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user…
Show active alerts from Bernstein - failed tasks, stalled agents, budget warnings, blocked tasks needing human intervention. Use…
Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent…
Show detailed cost breakdown and budget status for the Bernstein orchestrator. Use when the user asks about spending, budget,…
Create a new task in the Bernstein orchestrator. Use when the user wants to add a task, delegate work to an agent, file a bug…
Create and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when…
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…
Create a new Architecture Decision Record with sequential numbering and AgentDB registration