Cache Audit — Security skill for Claude Code
A Claude Code skill that audits your setup against the 6 prompt caching rules from Anthropic's engineering team.
How to install Cache Audit
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open ussumant/cache-audit and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Cache Audit does
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.
Alternatives in Security
- Anthropic Cybersecurity Skills — 734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work 3.8k ★
- Pocketpaw — Your AI agent in 30 seconds 775 ★
- Data Viz Audit — Audit a data visualization for chart type selection, accessible color palette, annotations, and anti-patterns 309 ★
README
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
Related Skills
Aiclean
Audit and clean up a Claude Code setup against Anthropic's current prompt-engineering guidance. Finds stale sc
Compliance Audit Skill
A Claude skill that audits your codebase for GDPR and EU AI Act compliance and returns a ranked list of fixes.
Claude Setup Audit
A Claude Code plugin that audits your whole setup — settings, permissions, hooks, MCP servers, skills, CLAUDE.
Cpv Batch Caching Audit
Fan out cpv-cache-optimizer-agent across every plugin in a marketplace, a list of plugins, or a single plugin.
UX Critique
Open-ended taste call on a specific surface. Not a structured audit — a designer's opinion. Returns 3 wins, 3
Claim Audit
A Claude skill that audits AI-written text claim by claim: quotes each checkable claim, tags it with one of te
Related Agents
LLM Integrator
LLM integration specialist who connects to OpenAI/Anthropic/Ollama APIs, designs prompt templates, implements
Streamlit Reviewer
Expert review specialist for Streamlit apps. Proactively audits a diff for execution-model bugs — the whole sc
LLM Orchestrator
Use this agent for LLM integration work — prompt engineering, multi-provider abstraction (OpenRouter, Gemini,