Updated 1mo ago
by OnlyTerp
prompt-cache-skills
Drop-in prompt-caching fixes for the LLM agent harness you use. Point your AI coding agent at this repo and it ships the patches.
115 GitHub stars (115)
+1 in 20 days
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | 0 |
| Sep 29 | 0 |
| Sep 30 | 0 |
| Oct 1 | 0 |
| Oct 2 | −1 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | −1 |
| Oct 7 | +2 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | +1 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 14 skills (14 skills found in its SKILL.md files)
- 10 forks (10 forks)
- 1mo ago last update (Last updated 1mo ago)
Install
Skills CLI
npx skills add OnlyTerp/prompt-cache-skills
Asks which skills and agents to install. Just one: npx skills add OnlyTerp/prompt-cache-skills --skill '<skill-slug>' — add -g for every project.
Claude Code
git clone https://github.com/OnlyTerp/prompt-cache-skillscp -r "prompt-cache-skills/skills/_TEMPLATE" ~/.claude/skills/
Copies the <skill-slug> skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add OnlyTerp/prompt-cache-skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
<skill-slug>
One-line description of what this fix does and why it matters.
skills/_TEMPLATE/SKILL.md on GitHub (opens in a new tab) -
aider-1h-ttl
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
skills/aider-1h-ttl/SKILL.md on GitHub (opens in a new tab) -
aider-cache-default-on
Aider's --cache-prompts is off by default. Flip it on for supported models.
skills/aider-cache-default-on/SKILL.md on GitHub (opens in a new tab) -
cline-fix-volatile-msg
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
skills/cline-fix-volatile-msg/SKILL.md on GitHub (opens in a new tab) -
cline-openai-cache-key
Cline OpenAI native provider sends no prompt_cache_key. Add a stable per-task key so cached_tokens stops being zero.
skills/cline-openai-cache-key/SKILL.md on GitHub (opens in a new tab) -
cline-pin-timestamp
Cline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.
skills/cline-pin-timestamp/SKILL.md on GitHub (opens in a new tab) -
continue-enable-defaults
Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.
skills/continue-enable-defaults/SKILL.md on GitHub (opens in a new tab) -
continue-fix-volatile-msg
Ladder-aware Continue Anthropic caching — verify the rolling ladder on the wire, then enable it by default and add TTL coverage.
skills/continue-fix-volatile-msg/SKILL.md on GitHub (opens in a new tab) -
continue-gemini-explicit
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.
skills/continue-gemini-explicit/SKILL.md on GitHub (opens in a new tab) -
opencode-bedrock-doc-blocks
OpenCode places cachePoint on Bedrock messages containing DocumentBlocks, which produces a "nothing available to cache" error.
skills/opencode-bedrock-doc-blocks/SKILL.md on GitHub (opens in a new tab) -
opencode-detect-openai-compat
OpenCode's caching detection misses OpenAI-compatible proxies routing to Anthropic/Bedrock. Broaden the predicate.
skills/opencode-detect-openai-compat/SKILL.md on GitHub (opens in a new tab) -
opencode-mistral-cache-key
OpenCode doesn't set prompt_cache_key for Mistral models, missing the documented 10% cached-token discount.
skills/opencode-mistral-cache-key/SKILL.md on GitHub (opens in a new tab) -
roo-bedrock-custom-arn
Roo Code's Bedrock provider silently disables caching for custom ARNs. Populate cachableFields to fix.
skills/roo-bedrock-custom-arn/SKILL.md on GitHub (opens in a new tab) -
roo-fix-volatile-msg
Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).
skills/roo-fix-volatile-msg/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
-
cavemanby JuliusBrussee 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
-
frontend-slidesby zarazhangrui Create beautiful slides on the web using a coding agent's frontend skills
-
Claude-Code-Game-Studiosby Donchitos Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio h…
-
cc-hahaby NanmiCoder 本地优先的跨平台 Claude Code / AI Agent 桌面工作台：多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物；支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude…