Claude API
Kocoro-lab/Kocoro
Build apps with the Claude API or Anthropic SDK. An agent skill from Kocoro-lab/Kocoro.
Patch guide for adding a stable per-task prompt_cache_key to Cline's OpenAI native provider so cached token counts stop reading as zero.
Install Cline OpenAI Prompt Cache Key Fix
$ npx skills add OnlyTerp/prompt-cache-skills --skill cline-openai-cache-key -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install OnlyTerp/prompt-cache-skills cline-openai-cache-key --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/OnlyTerp/prompt-cache-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cline-openai-cache-key .claude/skills/cline-openai-cache-key && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cline-openai-cache-key" agent skill from https://github.com/OnlyTerp/prompt-cache-skills/tree/main/skills/cline-openai-cache-key into .claude/skills/cline-openai-cache-key/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cline-openai-cache-key", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/OnlyTerp/prompt-cache-skills/tree/main/skills/cline-openai-cache-keyType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add OnlyTerp/prompt-cache-skills --skill cline-openai-cache-key -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install OnlyTerp/prompt-cache-skills cline-openai-cache-key --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OnlyTerp/prompt-cache-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/cline-openai-cache-key .agents/skills/cline-openai-cache-key && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cline-openai-cache-key" agent skill from https://github.com/OnlyTerp/prompt-cache-skills/tree/main/skills/cline-openai-cache-key into .agents/skills/cline-openai-cache-key/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cline-openai-cache-key", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OnlyTerp/prompt-cache-skills --skill cline-openai-cache-key -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install OnlyTerp/prompt-cache-skills cline-openai-cache-key --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OnlyTerp/prompt-cache-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/cline-openai-cache-key .cursor/skills/cline-openai-cache-key && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cline-openai-cache-key" agent skill from https://github.com/OnlyTerp/prompt-cache-skills/tree/main/skills/cline-openai-cache-key into .cursor/skills/cline-openai-cache-key/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cline-openai-cache-key", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/OnlyTerp/prompt-cache-skills.git --path skills/cline-openai-cache-key--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add OnlyTerp/prompt-cache-skills --skill cline-openai-cache-key -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install OnlyTerp/prompt-cache-skills cline-openai-cache-key --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OnlyTerp/prompt-cache-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/cline-openai-cache-key .gemini/skills/cline-openai-cache-key && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cline-openai-cache-key" agent skill from https://github.com/OnlyTerp/prompt-cache-skills/tree/main/skills/cline-openai-cache-key into .gemini/skills/cline-openai-cache-key/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cline-openai-cache-key", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install OnlyTerp/prompt-cache-skills cline-openai-cache-keyInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add OnlyTerp/prompt-cache-skills --skill cline-openai-cache-key -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/OnlyTerp/prompt-cache-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/cline-openai-cache-key .github/skills/cline-openai-cache-key && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cline-openai-cache-key" agent skill from https://github.com/OnlyTerp/prompt-cache-skills/tree/main/skills/cline-openai-cache-key into .github/skills/cline-openai-cache-key/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cline-openai-cache-key", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add OnlyTerp/prompt-cache-skills --skill cline-openai-cache-key -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install OnlyTerp/prompt-cache-skills cline-openai-cache-key --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OnlyTerp/prompt-cache-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/cline-openai-cache-key .opencode/skills/cline-openai-cache-key && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cline-openai-cache-key" agent skill from https://github.com/OnlyTerp/prompt-cache-skills/tree/main/skills/cline-openai-cache-key into .opencode/skills/cline-openai-cache-key/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cline-openai-cache-key", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
cline-openai-cache-key- GitHub stars
- 114
- Token cost
- ~868 tokens
- SKILL.md length
- 283 words
- Files
- 1
- Skills in repo
- 13
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Patch guide for adding a stable per-task prompt_cache_key to Cline's OpenAI native provider so cached token counts stop reading as zero.
- Works in 5 steps: Start mitmproxy capture as before. → Configure Cline with an OpenAI model… → Send two identical prompts in the same… → …
- Cline reports zero cached tokens with an OpenAI model
- SKILL.md covers Target, Symptom, Fix and Verify, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This skill describes one specific fix to src/core/api/providers/openai-native.ts in the cline/cline repository. Cline's OpenAI native provider only reads cache statistics from responses and never enables caching, so no prompt_cache_key goes out on Responses API calls, and hit rates stay low and unpredictable because requests are routed across pods at random.
The fix sets a stable prompt_cache_key derived from the task ID, or from a hash of the system instructions when there is no task ID, and warns never to use a per-request UUID. On the legacy Chat Completions endpoint the field is not valid, so the only lever is a stable prefix without timestamps, session IDs or random content. Verification means capturing traffic with mitmproxy, sending two identical prompts in one task, confirming the key and system prompt match across them, and seeing cached_tokens above zero with a ratio of at least 0.5 on a steady-state turn.
When your agent uses it
- Cline reports zero cached tokens with an OpenAI model
- Adding a prompt_cache_key to Responses API calls in an agent harness
- Checking that two identical prompts in one task hit the cache
Example prompts
- “Patch Cline's openai-native.ts to send a stable prompt_cache_key per task.”
- “Why does Cline report cached_tokens as zero with my OpenAI model?”
- “Verify with mitmproxy that the cache key is identical across two prompts in one task.”
Requirements
- A checkout of cline/cline containing the openai-native.ts provider
- mitmproxy for the verification step
- An OpenAI model configured in Cline
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Start mitmproxy capture as before.
- Configure Cline with an OpenAI model (gpt-5.4, gpt-5-codex, etc.).
- Send two identical prompts in the same task.
- Inspect captured requests
- Inspect responses
What it can do on your machine
Read from SKILL.md and the folder at commit 5b58ae2. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript and diff).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Cline OpenAI Prompt Cache Key Fix loads about 868 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 283 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 283 words (~868 tokens).
- name
- cline-openai-cache-key
- target_harness
- Cline
- target_repo
- cline/cline
- target_files
- src/core/api/providers/openai-native.ts
- target_commit
- 65e9727c (verify current at apply time)
- estimated_savings
- 50-90% input discount on OpenAI calls (currently 0%)
Files
Just SKILL.md in skills/cline-openai-cache-key of OnlyTerp/prompt-cache-skills.
Open the folder on GitHubat commit 5b58ae2
Compare with similar skills
Cline OpenAI Prompt Cache Key Fix next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cline OpenAI Prompt Cache Key Fix this skillOnlyTerp/prompt-cache-skills | 114 | — | ~868 | Automated safety check: Pass | Custom licence | |
| Claude APIKocoro-lab/Kocoro | 414 | 7 repos | ~4.5k | Automated safety check: Pass | Apache-2.0 | |
| Azure Openai To Responsesmicrosoft/ai-agents-for-beginners | 77k | — | ~6k | Automated safety check: Notes | MIT | |
| Claude APIloulanyue/awesome-claude-notes | 272 | 2 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Azure Openai To Responsesmicrosoft/ai-agents-for-beginners | 77k | — | ~6k | Automated safety check: Notes | MIT | |
| Mmsp TypescriptPrism-Shadow/model-message-stream-protocol | 113 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Azure Openai To Responses
microsoft/ai-agents-for-beginners
Migrate Python apps from Azure OpenAI Chat Completions to the Responses API.
Claude API
loulanyue/awesome-claude-notes
Anthropic Claude API patterns for Python and TypeScript. An agent skill from loulanyue/awesome-claude-notes.
- Official
Azure Openai To Responses
microsoft/ai-agents-for-beginners
Shift Python apps dem from Azure OpenAI Chat Completions go Responses API.
Mmsp Typescript
Prism-Shadow/model-message-stream-protocol
Guidance for using the MMSP TypeScript SDK (@prismshadow/mmsp).
ClawRouter LLM Gateway
BlockRunAI/ClawRouter
Describes ClawRouter, a local proxy that forwards each LLM request to the blockrun.ai gateway, which routes to a cheaper capable model, paid by USDC wallet or API key credit.
More from OnlyTerp/prompt-cache-skills
All 13 skills in this repoAider One-Hour Cache TTL
OnlyTerp/prompt-cache-skills
Patches Aider to request Anthropic's one-hour prompt cache lifetime, so long pauses between turns no longer expire the cache or need paid keepalive pings.
Aider Prompt Caching Default
OnlyTerp/prompt-cache-skills
Patch recipe that turns on Aider's --cache-prompts by default for models that support caching, with a verification procedure against the wire request.
Cline Prompt Cache Ladder Check
OnlyTerp/prompt-cache-skills
Verifies how Cline marks Anthropic prompt-cache breakpoints on the wire, then adds a tools breakpoint and tunes the cache TTL in its AI SDK code.
Cline Pin Timestamp
OnlyTerp/prompt-cache-skills
Cline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.
Continue Enable Defaults
OnlyTerp/prompt-cache-skills
Continue's prompt caching is opt-in via config and off by default.
Continue Gemini Explicit
OnlyTerp/prompt-cache-skills
Continue's Gemini provider doesn't use the cachedContents API at all.
Related
Works with
Categories
Questions about Cline OpenAI Prompt Cache Key Fix
What does Cline OpenAI Prompt Cache Key Fix do?
Patch guide for adding a stable per-task prompt_cache_key to Cline's OpenAI native provider so cached token counts stop reading as zero. ts in the cline/cline repository. Cline's OpenAI native provider only reads cache statistics from responses and never enables caching, so no prompt_cache_key goes out on Responses API calls, and hit rates stay low and unpredictable because requests are routed across pods at random.
When should I use Cline OpenAI Prompt Cache Key Fix?
Cline OpenAI Prompt Cache Key Fix fits situations like: cline reports zero cached tokens with an OpenAI model; adding a prompt_cache_key to Responses API calls in an agent harness; checking that two identical prompts in one task hit the cache.
How do I install Cline OpenAI Prompt Cache Key Fix in Claude Code?
Run `npx skills add OnlyTerp/prompt-cache-skills --skill cline-openai-cache-key -a claude-code`. Or copy the skill folder (skills/cline-openai-cache-key in OnlyTerp/prompt-cache-skills) into .claude/skills/cline-openai-cache-key in your project. Claude Code loads it when a task matches its description.
How do I install Cline OpenAI Prompt Cache Key Fix in Codex?
Run `npx skills add OnlyTerp/prompt-cache-skills --skill cline-openai-cache-key -a codex`. Or copy the skill folder (skills/cline-openai-cache-key in OnlyTerp/prompt-cache-skills) into .agents/skills/cline-openai-cache-key in your project. Codex loads it when a task matches its description.
Can I use Cline OpenAI Prompt Cache Key Fix in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OnlyTerp/prompt-cache-skills --skill cline-openai-cache-key -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cline-openai-cache-key, .gemini/skills/cline-openai-cache-key, .github/skills/cline-openai-cache-key and .opencode/skills/cline-openai-cache-key in your project.
What does Cline OpenAI Prompt Cache Key Fix need to run?
SKILL.md names no scripts, command-line tools or credentials: Cline OpenAI Prompt Cache Key Fix is instructions for the agent only. Our summary lists: A checkout of cline/cline containing the openai-native.ts provider; mitmproxy for the verification step; An OpenAI model configured in Cline.
Does Cline OpenAI Prompt Cache Key Fix access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Cline OpenAI Prompt Cache Key Fix safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Cline OpenAI Prompt Cache Key Fix use?
Cline OpenAI Prompt Cache Key Fix has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Cline OpenAI Prompt Cache Key Fix use?
About 868 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Cline OpenAI Prompt Cache Key Fix?
Skills that share tags, products or a category with Cline OpenAI Prompt Cache Key Fix: Claude API (Kocoro-lab/Kocoro, 414 stars), Azure Openai To Responses (microsoft/ai-agents-for-beginners, 77k stars), Claude API (loulanyue/awesome-claude-notes, 272 stars) and Azure Openai To Responses (microsoft/ai-agents-for-beginners, 77k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cline OpenAI Prompt Cache Key Fix?
OnlyTerp (a GitHub user) maintains it in OnlyTerp/prompt-cache-skills, which has 114 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on August 29, 2026.
Source: OnlyTerp/prompt-cache-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.