- Home
- Skills
- Workflow Automation
- claude-prompt-cache-hints
Claude Prompt Cache Hints
Automatic Claude prompt-cache breakpoint placement for the Anthropic API and Claude Code — save tokens without changing your code.
$4.90
Works with the AI Agents you already use
claude-prompt-cache-hints
Example session with this skill installed
Import cache_hints, pass your Anthropic Messages API payload, and it automatically marks stable prefixes with cache breakpoints before you send the request.
- Read your context and instructions
- Compiled the claude-prompt-cache-hints
The payload's system block, tools, and older conversation turns get cache_control markers. Runtime timestamps stay outside the cache boundary. Provider-reported cache hits reduce your token costs.
Connects securely to your tools. The creator never sees your data.
About this skill
Automatic Claude prompt-cache breakpoint placement for the Anthropic Messages API and Claude Code.
Places explicit cache breakpoints on stable system instructions, tools, and older conversation turns while keeping the current user turn and runtime timestamps outside the cache boundary. Existing client breakpoints are preserved, and the module never exceeds four explicit breakpoints.
Two entry points:
cache_hints.anthropic(payload, ttl='5m')— mutates an Anthropic Messages API payload in-place. Returns whether it changed.cache_hints.openai(payload, config, active_text)— returns a copy of an OpenAI-compatible payload with cache hints added. Only applies to models containing "claude".
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed today
- Software
Python 3.8+httpxstarletteuvicorn (proxy only)
Permissions
Allowed Hosts
The core module modifies request payloads in memory only. The optional proxy forwards to your configured upstream and logs token counters (never prompts or credentials).