Security & Testing Agent Skills for Codex CLI

Safety guardrails for destructive commands. (gstack)

Chrome Extension auth with @clerk/chrome-extension -- popup/sidepanel

Agent skill for code-analyzer - invoke with $agent-code-analyzer

MUST USE for any real runtime debugging across ANY language or binary — crashes, silent failures, wrong responses, stuck processes, memory…

Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure…

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.

Orchestrate E2E test triage and fix implementation: runs triage-ci then implement sequentially.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics…

Go testing best practices including table-driven tests, test helpers, benchmarking, race detection, coverage analysis, and integration…

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute.

Advanced Next.js patterns - middleware, Server Actions, caching with

Meta's 86M prompt injection and jailbreak detector.

Python testing best practices using pytest including fixtures, parametrization, mocking, coverage analysis, async testing, and test…

Autonomous multi-app QA sweep that drives template apps with Playwright MCP.

Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when…

Focused security audit of code, calibrated to surface real exploitable bugs and suppress theoretical findings.

Review Langfuse changes for SSRF, tenant isolation, secret handling, unsafe redirects or uploads, and RBAC drift.

Define and enforce policies, access controls, and compliance rules over Semantica knowledge graphs.

Create a Mastra project using create-mastra and smoke test the studio in Chrome using Chrome MCP server