Prompt caching — LLM caching strategies and patterns
Cut LLM costs with prompt, response and KV caching — Anthropic prompt caching, CAG patterns and cache invalidation
- What
- Cut LLM costs with prompt, response and KV caching — Anthropic prompt caching, CAG patterns and cache invalidation
- Cost
- Free
- Needs
- access to an LLM API whose caching features you want to use (e.g. Anthropic prompt caching) — the skill is strategy guidance, not software
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @sickn33's prompt-caching skill (adapted from vibeship-spawner-skills, Apache 2.0): LLM-specific caching strategies — Anthropic's native prompt caching for stable prefixes, response caching (Redis/Upstash patterns), KV-cache concepts, Cache-Augmented Generation (CAG) patterns and cache invalidation — with scope boundaries (no CDN or database query caching) and a recommended companion skill for context-window management. Honest caveats: provider pricing and cache mechanics change fast — treat the patterns as principles and check current provider docs; a real LLM API key is needed to use any of it. MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Prompt caching is a free Muse skill for cutting LLM costs with prompt, response and KV caching, covering Anthropic's native prompt caching for stable prefixes, response caching with Redis and Upstash patterns, KV-cache concepts, Cache-Augmented Generation patterns and cache invalidation. It sets scope boundaries excluding CDN and database query caching, and recommends a companion skill for context-window management.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit b84d35aStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: access to an LLM API whose caching features you want to use (e.g. Anthropic prompt caching) — the skill is strategy guidance, not software Install "Prompt caching — LLM caching strategies and patterns" for me. It gives my agent @sickn33's LLM caching playbook (adapted from vibeship-spawner-skills, Apache 2.0): Anthropic's native prompt caching for stable prefixes, response caching (Redis/Upstash patterns), KV-cache concepts, Cache-Augmented Generation (CAG) patterns and cache invalidation, with scope boundaries (no CDN or DB query caching) and a recommended context-window-management companion. MIT-licensed. Repository: https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/b84d35abf733cbbc3400dbc0e16fbbdc2a4fe97e/plugins/agentic-awesome-skills-claude/skills/prompt-caching/SKILL.md Pinned version: install the code at commit b84d35abf733cbbc3400dbc0e16fbbdc2a4fe97e exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "prompt-caching". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. provide my LLM API key via the secure vault and tell the agent which prompts to cache; nothing else — it's a strategy guide). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- b84d35a · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.