A review tool for checking whether Claude Code's prompt cache is being used effectively. Prompt caching reuses stable instructions so repeated requests do not need to process them again.

Use it to audit prompt ordering, tool stability, dynamic content, and hook-injected instructions, then receive a scored report with suggested fixes.

It identifies configuration patterns that can reduce cache reuse, such as changing content in the wrong place or unstable tool definitions.

cache-audit — Skill for Claude Code and Codex by pantheon-org: A review tool for checking whether Claude Code's prompt…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/pantheon-org/tekhne/cache-audit

Any agent

npx skills add pantheon-org/tekhne --skill cache-audit

Clone the repo

git clone --depth 1 https://github.com/pantheon-org/tekhne

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pantheon-org/tekhne/cache-audit.svg)](https://agentmods.dev/skills/pantheon-org/tekhne/cache-audit)

Your own site

<a href="https://agentmods.dev/skills/pantheon-org/tekhne/cache-audit"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/cache-audit.svg" alt="Measured on agentmods" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,110 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00038	$0.02110
Opus 5	$0.00019	$0.01055
Sonnet 5	$0.00008	$0.00422
Haiku 4.5	$0.00004	$0.00211

Measured 5d ago against content hash f95a50dda311, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cache-audit scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Read:** `~/.claude/settings.json`, all active `CLAUDE.md` files in the project hierarchy

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/agentic-harness/cache-audit/SKILL.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Cache Audit Skill

Trigger: /cache-audit or "audit my caching" or "check my cache setup" or "am I breaking the cache?"

What it does: Reads your live Claude Code configuration and checks it against the 6 prompt caching rules from Anthropic's engineering team. Returns a scored report with specific, actionable fixes.

Reference: Based on Thariq Shihipar's thread "Lessons from Building Claude Code: Prompt Caching Is Everything"

When Invoked

Run all checks automatically. Do not ask for confirmation. Read the relevant files and produce the full report in one pass.

The 6 Checks

Check 1 — Prompt Ordering (Static Before Dynamic)

Read: ~/.claude/settings.json, all active CLAUDE.md files in the project hierarchy

What to look for:

Does the system prompt load in the right order? Rule: static content first, dynamic content last
Correct order: System prompt → Tools → CLAUDE.md → Session context → Messages
Flag: Any dynamic content (timestamps, git status, current date, user stats) appearing in the system prompt itself
Flag: CLAUDE.md files that include session-specific or time-sensitive data
Pass: CLAUDE.md files that are purely static instructions, conventions, and file references

Scoring:

PASS: System prompt is fully static, dynamic data injected via messages
WARNING: Some dynamic data in system prompt but low-frequency change
FAIL: High-churn dynamic content (timestamps, file contents) in system prompt

Check 2 — Dynamic Updates via Messages (not System Prompt Edits)

Read: All hook files listed under SessionStart and UserPromptSubmit in ~/.claude/settings.json

What to look for:

Hooks should output dynamic data as additionalContext in their JSON response (which becomes a <system-reminder> message) — not by modifying the system prompt
Check each hook's output format: does it use hookSpecificOutput.additionalContext? ✅
Flag: Any hook that writes to a system prompt file, modifies CLAUDE.md, or injects into the static prefix
Pass: Hooks that return JSON with additionalContext key

Read the full file on GitHub · 216 lines

Files

What ships with it

12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago First seen · 216 lines · 38 tokens per session scan A f95a50dda311

Subscribe to this mod's changes

cache-audit is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 2,110 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents agent-skills skills tessl

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…

anthropics/claude-plugins-official · 82 tokens

gke-reliability

Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).

google/skills · 73 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…

google/skills · 181 tokens

cache-audit