Agent Skill Bundle — Security skill for Claude Code
174 AI agent skills for Antigravity, Codex & Claude Code.
How to install Agent Skill Bundle
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open ZAX-MILLION/agent-skill-bundle and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agent Skill Bundle does
174 AI agent skills for Antigravity, Codex & Claude Code. Strict on-demand loading, preserved upstream attribution, and review-first security.
Alternatives in Security
- Agent Memory Vault — Markdown-first shared memory vault for Claude Code and Codex with SQLite, Zvec, Git, closeout, and audit 314 ★
- Claude Leaked Files — Mirrored snapshot of Claude Code's source (exposed 2026-03-31) preserved for educational purposes, defensive s 256 ★
- Skill Threat Modeling — Code-First Deep Risk Analysis Skill for Claude Code - 8-Phase Workflow with Security design review, STRIDE Thr 207 ★
README
Agent Skill Bundle

**188 reviewed agent-skill directories. One source vault. Two native bootstrap skills.**
A source-preserving collection of reusable AI agent workflows for **Google Antigravity, OpenAI Codex, Claude Code**, and other file-based Agent Skills hosts. Find the skill you need without loading the entire collection into the agent's native startup discovery.
Original authors retain credit. Skills, supporting files, license notices, and reviewed source revisions stay traceable. Host adapters are separate from upstream copies.
[Quick start](#quick-start-strict-on-demand) · [What's included](#whats-included) · [External tools](#skills-are-not-software) · [Security](SECURITY.md) · [Upstream credits](CREDITS.md) · [Source review](docs/REVIEW_2026-09-27.md)
At a glance
| 188 skill directories | The complete reviewed source vault, including local adapters. |
| 2 native bootstraps | i-have-adhd and skill-retrieval-routing in strict on-demand mode. |
| 186 on-demand entries | Remain in the source checkout; local Skill Retrieval MCP must be configured separately for searchable access. |
| 3 primary hosts | Antigravity IDE, Codex, and Claude Code, using the same portable skill content. |
| Explicit setup only | The installer copies selected skill directories when you run it; it does not register an MCP service, activate cloud accounts, install external executables, or read credentials. |
Why strict on-demand?
Installing 188 skills natively exposes their descriptions to host discovery. The preferred setup exposes only **two** bootstrap descriptions from this bundle. When a task needs something specific, the separately configured local retrieval service finds the relevant skill; the agent then reads that skill and its supporting files from the **one source checkout**.
This keeps d
Related Skills
Review Frontend Performance
Audit frontend performance: bundle size and code splitting, render waterfalls, N+1 data fetching, unmemoized w
Yakos
Multi-runtime agent framework (Claude Code, Codex, Antigravity) with hard/soft controls, audit-first hooks, an
Senior Engineering Partner
A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/A
Clanker Skills
Evidence-first agent skills for Codex, Claude Code, OpenCode, Pi, and Grok: planning, code review, call-chain
Production Agent Skills
High-reliability, deterministic Agent Skills for autonomous AI coding agents (Antigravity, Claude Code, Cursor
Save My Disk
Universal AI Agent skill & runbook for intelligent, non-invasive disk audit and safe optimization. Supports An
Related Agents
Security Sentinel
Deep security review focused on OWASP Top 10, injection, auth/authz, data exposure, and dependency vulnerabili
Paf Reviewer
Runs one phone-a-friend relay or review command in the background and reports back a receipt plus the findings
Verify
Claude Code runner adapter. 격리 snapshot에서 Codex/Antigravity/Tailscale Aperture reviewer를 조합해 교차검증. 보안 결정권 없음,