Security collection

Security and Code Review Skills for Claude Code and Antigravity

For developers who want their coding agent to audit code, review pull requests and check that security fixes really landed. To install one, download it and put the skill folder (the one with SKILL.md) in your agent’s skills directory: .claude/skills/ for Claude Code or .agents/skills/ for Antigravity. The install guide covers global folders and CLI options.

Updated November 2026

At a glance

SkillBest forAuthor
Security AuditEvidence-backed code auditsAntigravity Skills
Code ReviewerPull request reviewAntigravity Skills
Code Review and QualityStructured review verdictsAntigravity Skills
007Threat modeling and OWASP checksAntigravity Skills
Fix ReviewVerifying security fixesAntigravity Skills
Agentic Actions AuditorSecuring agent CI workflowsAntigravity Skills
Accessibility Audit and TestingWCAG accessibility auditsAntigravity Skills
AegisOps AIInfrastructure security and cost auditsAntigravity Skills
Devcontainer SetupSandboxed agent workspacesAntigravity Skills

Which security skill fits your job?

The 9 security and review skills

  1. Published by Antigravity Skills · Evidence-backed code audits

    Evidence-first security review of your code with sandbox-only execution, ending in one Markdown report. Based on Cloudflare’s open-source security-audit-skill (MIT).

    Use it when: You need a security pass on a codebase and want findings backed by evidence, not guesses.

  2. Published by Antigravity Skills · Pull request review

    Reviews pull requests, enforces coding standards, flags anti-patterns and generates quality reports.

    Use it when: A complex PR needs a careful review against your team’s standards.

  3. Published by Antigravity Skills · Structured review verdicts

    Reviews any diff or PR on five axes with severity-labelled, evidence-backed findings, a fixed report format and a clear verdict.

    Use it when: You want every review to come back in the same format with a clear ship or fix decision.

  4. 04

    007

    Published by Antigravity Skills · Threat modeling and OWASP checks

    A broad security audit across eight domains, including OWASP Top 10, STRIDE and PASTA threat modeling and incident response, with red and blue team analysis.

    Use it when: You want a threat model and an OWASP-style audit for a whole project.

  5. Published by Antigravity Skills · Verifying security fixes

    Checks that fix commits actually address the audit findings they claim to fix, without introducing new bugs or regressions.

    Use it when: An audit is done, fixes have landed, and you need to confirm each finding is really closed.

  6. Published by Antigravity Skills · Securing agent CI workflows

    Audits CI/CD pipelines for attack vectors in AI-agent workflows such as Claude Code and Gemini actions.

    Use it when: Your CI runs AI agents on pull requests or issues and you want to know how they could be abused.

  7. Published by Antigravity Skills · WCAG accessibility audits

    Audits web and mobile apps for WCAG compliance with automated scans, manual checks, remediation and re-testing.

    Use it when: You need to find and fix accessibility problems before a release or a compliance review.

  8. Published by Antigravity Skills · Infrastructure security and cost audits

    Automates security and cost audits across Linux kernel patches, Terraform cost drift and Kubernetes compliance.

    Use it when: Your infrastructure changes need both a security check and a cost check.

  9. Published by Antigravity Skills · Sandboxed agent workspaces

    Creates devcontainers with Claude Code, language tooling for Python, Node, Rust or Go, and persistent volumes for sandboxed workspaces.

    Use it when: You want the agent to run inside an isolated container instead of directly on your machine.

How to install these skills

Put each skill folder (the one that contains SKILL.md) in your agent’s skills folder: .agents/skills/ in your project for Antigravity and Codex, or .claude/skills/ for Claude Code. The install guide covers global folders, CLI commands and a full worked example.

Read the install guide

Frequently asked questions

Which security skill should I start with?
Security Audit for an evidence-first review of your own code, then Fix Review once the fixes land. Add Code Review and Quality if you want every pull request reviewed in the same format.
Do these skills run attacks against my systems?
They are review and audit workflows for your own code and infrastructure. Security Audit, for example, only executes code inside a sandbox. Read each skill page before installing so you know what it runs.
Do they work in both Claude Code and Antigravity?
Yes. They use the SKILL.md format that Claude Code, Antigravity and Codex all read; only the folder you install them into differs.
How do I install these skills?
Download the skill and put its folder (the one that contains SKILL.md) in your agent’s skills directory: .claude/skills/ for Claude Code, or .agents/skills/ in your project for Antigravity and Codex. The install guide at /docs/install-skills lists global folders and CLI options.
What does a download cost?
Each packaged skill download on Antigravity Skills uses 1 credit. The skill pages and the install guide are free to read.