skills.rest
OnlyTerp
OnlyTerpCOMMUNITY
Explore all skills by this author →
GitHub

cline-openai-cache-key

Add a stable prompt_cache_key to Cline's OpenAI native provider.

113|8|Updated May 28, 2026
Search Tags:#OpenAI#AI agent#prompt caching#cache hit rates#Cline
One-click install
npx skills add https://github.com/OnlyTerp/prompt-cache-skills --skill cline-openai-cache-key
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cline-openai-cache-key
Source: https://github.com/OnlyTerp/prompt-cache-skills/tree/main/skills/cline-openai-cache-key
Command: npx skills add https://github.com/OnlyTerp/prompt-cache-skills --skill cline-openai-cache-key

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Cline's OpenAI native provider sends no prompt_cache_key, leading to zero cache hits. This Skill adds a stable cache key to solve this issue.

Core Features & Use Cases

  • Stable Cache Key: Adds a stable per-task key for the OpenAI native provider in Cline, ensuring cached_tokens are not zero.
  • Target Harness: Specifically designed for the Cline AI coding agent.
  • Use Case: If you're using Cline and facing low cache hit rates, this Skill can help you achieve 80-99% cache hit rates.

Quick Start

Apply the 'cline-openai-cache-key' Skill to your Cline setup to enhance OpenAI cache usage.

Frequently Asked Questions about cline-openai-cache-key

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
Why am I getting zero cache hits with the OpenAI native provider in Cline?▼

You get zero cache hits because Cline's OpenAI native provider sends no prompt_cache_key, preventing prompt caching. Adding a stable per-task cache key enables cached_tokens and boosts hit rates to 80-99%.

How do I enable prompt caching for the OpenAI Responses API in Cline?▼

To enable prompt caching for Cline's OpenAI Responses API, you must modify the openai-native.ts file to inject a stable prompt_cache_key. This ensures cached_tokens are not zero for AI agents.

Does adding a stable cache key to Cline require modifying internal files?▼

Yes, adding a stable cache key requires modifying the openai-native.ts file in your Cline setup. This targeted edit injects the prompt_cache_key needed by the OpenAI native provider to function properly.

What is the best way to improve OpenAI cache hit rates for Cline agents?▼

The best way to improve OpenAI cache hit rates for Cline agents is applying a stable prompt_cache_key. This targeted modification to the OpenAI native provider enables prompt caching and achieves 80-99% hit rates.

Can I use this prompt caching solution with other providers in Cline?▼

No, this solution is specifically designed for the Cline OpenAI native provider using the Responses API. It targets the openai-native.ts file to add a stable prompt_cache_key and does not support other providers.

Related Skills

Explore More Software Engineering Skills→
saddam-eng-techsaddam-eng-tech

agent-env-syncer

Generate unified workspace and per-agent configuration files for AI coding agents.

Community
Advanced
OnlyTerpOnlyTerp
113

opencode-mistral-cache-key

Set the prompt_cache_key for Mistral models in OpenCode's transform.ts file.

Community
Intermediate
jackzhaojinjackzhaojin
1

conversation-logger

Capture AI coding agent conversations as timestamped markdown logs.

Community
Intermediate
JGalegoJGalego
6

lineup

Compare model responses side by side via command-line interface.

Community
Intermediate