No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by joetawil7 · AI Skill · ★ 145
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is first-pass safe to install? View the security audit →
first-pass first-pass makes a coding agent check the code around a change, not only the lines it writes, and prove its work before it calls anything done. It's a Claude Code plugin; Cursor, Codex and other agents get the same rules and skills (the hooks are Claude Code only). You set it up once, in the folder that holds your repos. What it does Before code, the agent answers ten questions about the change against the real code: what happens if it runs twice, stops halfway, or an outside service times out; which other code uses the same data; what the user sees when it fails. Each answer is a , a test, or a gap you decide to accept. While building, anything the task didn't ask for (a helper, a cap, a retry, an option) has to earn its place. The agent asks whether it needs to exist, leaves it out when nothing requires it, and lists it under "Not built" so you can ask for it. A review finding gets fixed in code only when it breaks the task or a written promise, or does real harm; the rest are listed as open, with why. Before "done", a second agent that didn't write the code reviews it in a fresh context.
| Stars | 145 |
| Forks | 1 |
| Language | JavaScript |
| Category | AI Skill |
| License | MIT |
| Quality Score | 62.6778379690998/100 |
| Last Updated | 2026-10-01 |
| Created | 2026-09-25 |
| Platforms | claude-code, node |
| Est. Tokens | ~18k |
Looking for a first-pass alternative? If you're comparing first-pass with other ai skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP
Production-ready skills for Claude Code CLI - Cloudflare, React, Tailwind v4, and AI integrations
Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support
Development workflows for Claude Code that keep broad exploration focused on the outcome you approved.
Human + AI music production workflow for Suno - skills, templates, and tools
Learn practical techniques to enhance your AI-assisted development workflow with Claude Code.
Explore other popular ai skill tools:
first-pass is Rules and checks that make Claude Code look around a change, not just at the lines it writes: ten questions before code, a reviewer that didn't write it, proof before done, bugs fixed as a class.. It is categorized as a AI Skill with 145 GitHub stars.
first-pass is primarily written in JavaScript. It covers topics such as agents-skills, agentskill, agentskills.
You can find installation instructions and usage details in the first-pass GitHub repository at github.com/joetawil7/first-pass. The project has 145 stars and 1 forks, indicating an active community.
first-pass is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to first-pass on Agent Skills Hub include claude-elixir-phoenix, claude-skills, yume. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: