cipshadow

AI Spend — Security skill for Claude Code

Security community

Audit Claude Code token efficiency: MCP overhead, session patterns, skill cost, cache hit rate.

How to install AI Spend

Installs to ~/.claude/skills/cipshadow-leverage-and-taste-ai-spend/SKILL.md

Terminal

mkdir -p ~/.claude/skills/cipshadow-leverage-and-taste-ai-spend && curl -fsSL https://raw.githubusercontent.com/cipshadow/leverage-and-taste/HEAD/commands/ai-spend.md -o ~/.claude/skills/cipshadow-leverage-and-taste-ai-spend/SKILL.md

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

What AI Spend does

name: ai-spend description: Audit Claude Code token efficiency: MCP overhead, session patterns, skill cost, cache hit rate. Add --full for actual dollar spend if you have billing data access. model: sonnet user-invocable: true

Audit Claude Code token spend and surface efficiency wins. Quantify everything in dollars.

**Argument:** `$ARGUMENTS`

No argument → local-only audit (instant, no external queries)
--full → include Layer 1: actual dollar spend from your billing source

Alternatives in Security

MCP Security Checklist (SlowMist) — Comprehensive checklist: input validation, rate limiting, RBAC, credential management, container hardening 819 ★
ThinkWatch — Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII 817 ★
Engage.Exploit — Execute Phase 4 - Exploitation and Access Establishment 348 ★