Cache Audit

cache-audit — Prompt Caching Skill for Claude Code

A Claude Code skill that audits your setup against the 6 prompt caching rules from Anthropic's engineering team. Returns a scored report with specific fixes.

Why This Exists

Prompt caching is what makes Claude Code affordable at scale. A high cache hit rate reduces costs and latency dramatically — but it's surprisingly easy to break without knowing it.

The Anthropic team runs alerts on cache hit rates and treats drops as incidents. This skill brings the same discipline to your personal setup.

What It Checks

Rule	What breaks it
1. Ordering	Dynamic data (timestamps, git status) in the system prompt
2. Message injection	Editing the system prompt mid-session instead of using tags
3. Tool stability	Adding/removing tools mid-conversation
4. Model switching	Switching models in the same conversation thread
5. Dynamic content size	Injecting thousands of tokens of dynamic data per session
6. Fork safety	Compaction/subagent calls that don't share the parent's prefix

Installation

Global (applies to all projects)

mkdir -p ~/.claude/skills/cache-audit
curl -o ~/.claude/skills/cache-audit/SKILL.md https://raw.githubusercontent.com/ussumant/cache-audit/main/cache-audit/SKILL.md

Per-project

mkdir -p .claude/skills/cache-audit
curl -o .claude/skills/cache-audit/SKILL.md https://raw.githubusercontent.com/ussumant/cache-audit/main/cache-audit/SKILL.md

Then restart your Claude Code session for the skill to register.

Usage

/cache-audit

or say: `"audit my caching"` / `"check my cache setup"`

Example Output

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  PROMPT CACHE AUDIT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Score: 5/6

✅  Rule 1 — Ordering: PASS
✅  Rule 2 — Message injection: PASS
✅  Rule 3 — Tool stability: PASS
✅  Rule 4 — Model switching: PASS
⚠️  Rule 5 — Dynamic content size: W