Adversarial risk gate for AI coding agents — blocks actions until you approve.
skills is easy to set up with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
npx skills add carrilloapps/skillsRun the command in your terminal.
Confirm that the skill files were added to your agent workspace.
Check the README requirements before invoking the skill in your agent.
This tool adds a safety check before your AI coding agent takes any action. It intercepts plans, analyzes risks, and asks for your approval before proceeding. Works with Copilot, Claude, Cursor, Windsurf, and 40+ other agents.
carrilloapps/skills is a collection of agent skills for AI coding agents, providing adversarial analysis, security assessment, quality gates, and engineering best practices. The flagship skill is Devil's Advocate, a mandatory adversarial risk gate that intercepts every plan before execution and blocks all actions until you explicitly approve. It works with 40+ AI coding agents including GitHub Copilot, Claude Code, Cursor, Windsurf, Cline, Codex, and Gemini CLI. Other skills include sar-cybersecurity for automated security assessment reports mapped to 20+ compliance standards, and ai-rules for personal behavioral rules for AI tools. The tool is installed via npx and can be targeted to specific agents or globally.
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 76 days ago.
0 GitHub stars indicate community interest.
0 open issues signal maintenance load.
MIT license detected.
Prevent AI agents from executing risky operations without human approval
Add adversarial review to code generation workflows
Automate security assessments for AI-generated code
Enforce coding standards and best practices via AI rules
Generate post-incident analysis reports
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing.
Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
The tool intercepts all agent actions, which may slow down workflows if not configured properly.
Requires trust in the npx skills installer and the repository maintainer.
0
Stars
0
Forks
0
Issues
MIT
License
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.
Adversarial risk gate for AI coding agents — blocks actions until you approve.
Developers using AI coding assistants who want safety gates, Security engineers needing automated risk analysis for AI actions, Tech leads enforcing code quality and compliance in AI workflows
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing. Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
Similar or complementary options to evaluate include anthropic-skills, bug-hunter, Browser Act Skills.
Jun 7, 2026
4 security/trust notes recorded.
Setup difficulty is 2/5.
Browser automation CLI built for AI agents — breaks anti-bot walls, supports multi-session parallel execution.