Kit Audit — Security skill for Claude Code
Measure the factory-kit's token footprint — baseline vs on-demand, heaviest assets, trim candidates.
How to install Kit Audit
Installs to ~/.claude/skills/nonlinear-xyz-factory-kit-kit-audit/SKILL.md
mkdir -p ~/.claude/skills/nonlinear-xyz-factory-kit-kit-audit && curl -fsSL https://raw.githubusercontent.com/nonlinear-xyz/factory-kit/HEAD/commands/kit-audit.md -o ~/.claude/skills/nonlinear-xyz-factory-kit-kit-audit/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Kit Audit does
description: Measure the factory-kit's token footprint — baseline vs on-demand, heaviest assets, trim candidates argument-hint: (no arguments)
Load and follow the canonical `factory-kit-audit` skill. This adapter adds no behavior; the canonical skill owns the read-only audit and output shape.
Alternatives in Security
- Maestro Knowledge — Intent-driven knowledge-store and Run knowledge lifecycle management — audit/prune, stage candidates (with sig 530 ★
- Query Token Audit — Audit token security to detect scams, honeypots, and malicious contracts across BSC, Base, Solana, and Ethereu 483 ★
- Reflexion — Audit and optimize the .claude/ ecosystem — skills, hooks, guides, patterns, agents, and settings — for qualit 224 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Claude Trim
Audit your Claude Code token usage — see which skills eat your context budget and find conflicts before they c
Token Waste Audit
Run the FR-26 token-waste audit — parse this project's Claude Code transcripts deterministically (requestId-de
Agent Context Bench
Audit AGENTS.md, CLAUDE.md, Cursor and Copilot instructions; measure token cost and benchmark AI coding-agent
Audit Scenario
Audit dark-factory scenario file against Scenario Writing Guide
Audit Spec
Audit dark-factory spec file against preflight checklist and quality criteria
Claude Kit
1 Configuration factory for Claude Code -- 13 composable stacks, 6 agents, audit scoring, practices pipeline.
Related Agents
Token Auditor
Scans ui/src/ for hardcoded visual values, duplicate components, and shadcn replacement candidates; produces d
Context Auditor
Use proactively when the user wants to cut Claude Code token cost or asks "why is this session so expensive /
Echo Runner
Minimal mechanical runner — executes exactly the shell command given in the task prompt and relays its stdout