frankxai

Agent Quality — Security skill for Claude Code

Security community

Run the ACOS agent-quality audit — 9-check rubric over .claude/agents/.md, produces ranked priority queue.

How to install Agent Quality

Installs to ~/.claude/commands/frankxai-frankx.ai-vercel-website-agent-quality.md

Terminal

mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/frankxai/frankx.ai-vercel-website/HEAD/.claude/commands/agent-quality.md -o ~/.claude/commands/frankxai-frankx.ai-vercel-website-agent-quality.md

Restart Claude Code, or start a new session, for it to be picked up.

What Agent Quality does

description: Run the ACOS agent-quality audit — 9-check rubric over .claude/agents/*.md, produces ranked priority queue argument-hint: "[agent-name | --json | nothing for full audit]"

/agent-quality — ACOS Agent Quality Audit

Run the deterministic 9-check structural audit over every `.claude/agents/*.md` file. Surfaces which agents need revision first.

This is the **slash-command surface** for the audit. The `@meta-agent-quality-auditor` subagent uses the same script.

Workflow

Alternatives in Security

Portaljs Check Data Quality — Audit a local or remote tabular file (CSV/TSV) for common data quality issues 2.3k ★
Tech Debt Skill — Claude Code skill that produces a thorough, file-cited tech debt audit of an entire codebase 590 ★
Release Audit — Use right before cutting a release — it spawns ONE fresh sibling session via CCC that audits only the JUDGMENT 130 ★