Security & Testing Agent Skills

Sets a machine up with agentbox — a single bwrap wrapper that runs any coding-agent CLI (Claude Code, Pi, Codex) with the host environment…

Set up performance benchmarks and CodSpeed harness for a project.

Autonomous AI pentester for web apps and APIs.

Gate bounded commands on a multi-user AI/GPU host through scope, ownership, authorization, and resource controls.

Framework-level sharing and privacy for user-authored resources (dashboards, documents, forms, decks, etc.).

Use when adding or reviewing Bats tests for shell scripts, including fixtures, setup and teardown, exit-code assertions, output…

Use when an AI coding agent has fixed a bug or modified API/backend logic and you need to prevent the same class of bug from recurring…

Apply modern web development best practices for security, compatibility, and code quality.

Runs a tight four-phase loop — reproduce, isolate, diagnose, fix — to root-cause a single bug with evidence, not guesses.

Enforces a stop-the-line triage protocol across failure classes — test failures, build breaks, runtime errors, and production incidents…

Subjects a non-trivial decision to a fresh-context adversarial review before it stands, in-flight rather than as a post-hoc PR verdict.

Sets up eval-driven development (EDD) for an agent-assisted feature — define capability and regression evals before coding, grade them…

Runs a two-pass vulnerability scan on a snippet, file, or diff — a static pattern pass across fixed categories (injection, secrets, auth…

Hardens a feature against attack before or while it's built — threat-model trust boundaries with STRIDE, apply the Always/Ask-First/Never…

Reviews code for security vulnerabilities across Go, TypeScript, PHP, and infrastructure config.

Audits an agent harness's own configuration — CLAUDE.md, .claude/settings.json, MCP server configs, hooks, and agent definitions — for…

Drives development with tests written before implementation code, in Go, TypeScript, PHP, or any language.

Generates comprehensive unit, table-driven, and concurrency tests for a given function or module — happy paths, error paths, boundary…

Comprehensive web quality audit covering performance, accessibility, SEO, and best practices.

Disciplined diagnosis loop for hard bugs and performance regressions — builds a tight, red-capable feedback loop at the level the bug was…

It fixes the current repository until it's green. It detects the stack, runs tests, type checks, lint, and builds, fixes loop errors, and…