Agent skill

Cline Prompt Cache Ladder Check

by OnlyTerp in 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.

Custom licenceAuto-check passedAI & LLM Engineering

Install Cline Prompt Cache Ladder Check

skills CLI
$ npx skills add OnlyTerp/prompt-cache-skills --skill cline-fix-volatile-msg -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OnlyTerp/prompt-cache-skills cline-fix-volatile-msg --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OnlyTerp/prompt-cache-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cline-fix-volatile-msg .claude/skills/cline-fix-volatile-msg && rm -rf skills-src

Use ~/.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/

Facts

Skill name
cline-fix-volatile-msg
GitHub stars
114
Token cost
~2k tokens
SKILL.md length
791 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
Custom licence

At a glance

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.

  • Works in 3 steps: verify the ladder on the wire (before… → add the tools breakpoint (real,… → TTL: leave 5min for active loops, 1h…
  • Auditing whether Cline's prompt caching behaves as intended on the wire
  • SKILL.md covers Target, What Cline actually does…, Step 1 — verify the ladder on… and Step 2 — add the tools…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

After Cline moved to a monorepo built on the Vercel AI SDK, this skill became a patch-and-verify guide for the cline/cline repository. Earlier versions called Cline's habit of marking recent user messages a copy-paste bug; later analysis showed it is a deliberate rolling read/write ladder, so the current advice is to verify it rather than rip it out.

In the current code, `buildAiSdkRequestMessages` in `ai-sdk.ts` uses `applyPromptCacheToLastTextPart` from `anthropic-compatible.ts` to attach an ephemeral `cache_control` marker to the last text part of the last user message, for both the `anthropic` and `openaiCompatible` provider keys. That marker is the write point for a request; because it stays in history, it becomes the read point for the next one. The verification method carries over from the older two-marker layout even though file paths and wire shape changed.

When your agent uses it

  • Auditing whether Cline's prompt caching behaves as intended on the wire
  • Adding a cache breakpoint for tool definitions in Cline's Anthropic path
  • Tuning the cache TTL for requests that go to Anthropic or an OpenAI-compatible relay

Example prompts

  • “Check Cline's cache_control markers on the wire and confirm the read/write ladder holds.”
  • “Add a tools breakpoint to Cline's Anthropic request path.”
  • “Our Cline sessions miss the prompt cache too often. Find out why and tune the TTL.”

Requirements

  • A checkout of the cline/cline monorepo
  • A way to inspect the outgoing API requests

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. verify the ladder on the wire (before any change)
  2. add the tools breakpoint (real, verifiable win)
  3. TTL: leave 5min for active loops, 1h only for idle-heavy use

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 Prompt Cache Ladder Check loads about 2k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 791 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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 791 words (~2,020 tokens).

“sdk/packages/llms/src/providers/routing/anthropic-compatible.ts and sdk/packages/llms/src/providers/ai-sdk.ts in cline/cline (desktop-v0.0.20 monorepo, Vercel AI SDK path).”

— opening of SKILL.md by OnlyTerp, Custom licence
name
cline-fix-volatile-msg
target_harness
Cline
target_repo
cline/cline
target_files
sdk/packages/llms/src/providers/routing/anthropic-compatible.ts, sdk/packages/llms/src/providers/ai-sdk.ts
target_commit
desktop-v0.0.20 (monorepo restructure; old src/core/api path 404s)
estimated_savings
avoids a harmful "fix" + up to one free breakpoint on tools

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/cline-fix-volatile-msg of OnlyTerp/prompt-cache-skills.

Open the folder on GitHubat commit 5b58ae2

Compare with similar skills

Cline Prompt Cache Ladder Check 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.

Cline Prompt Cache Ladder Check compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cline Prompt Cache Ladder Check this skillOnlyTerp/prompt-cache-skills114—~2kAutomated safety check: PassCustom licence
Dt Obs GenaiDynatrace/dynatrace-for-ai161—~4.5kAutomated safety check: PassApache-2.0
Prefix Cache Replaybenchflow-ai/skillsbench1.8k—~2.3kAutomated safety check: PassApache-2.0
Cache Credits AnalyzerTsinHzl/kiro2cc-proxy164—~1.1kAutomated safety check: PassMIT
Prompt Cachingdavila7/claude-code-templates32k6 repos~452Automated safety check: PassMIT
LLM Cost Optimizationsickn33/agentic-awesome-skills47k1 repos~2.5kAutomated safety check: PassMIT

Similar skills

  • Dt Obs Genai

    Dynatrace/dynatrace-for-ai

    Analyze & debug GenAI/LLM apps: token cost & caching by prompt, model & provider; latency/errors; agent & tool loops/failures; conversations; guardrails; evaluations; OpenTelemetry/dt-evals setup.

    161 GitHub stars~4.5k tokensUpdated 7 days ago
    AI & LLM EngineeringAuto-check passed
  • Prefix Cache Replay

    benchflow-ai/skillsbench

    Replay an LLM inference request trace (Mooncake / vLLM / SGLang hashids format) against a block-level KV prefix cache and compute hit statistics.

    1.8k GitHub stars~2.3k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed
  • Cache Credits Analyzer

    TsinHzl/kiro2cc-proxy

    分析 kiro2cc-proxy 访问日志,计算 Prompt Caching 节省的 credits。只要用户粘贴了含有"输入token 输出token 费用$ credits✓"格式的日志行,并询问节省了多少credits、缓存效率、cost分析等,立即使用此 skill。触发关键词:节省了多少credits、cache节省、分析日志、caching…

    164 GitHub stars~1.1k tokensUpdated today
    Backend & APIsAuto-check passed
  • Prompt Caching

    davila7/claude-code-templates

    Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache…

    32k GitHub starsUsed in 6 repos~452 tokens
    Backend & APIsAuto-check passed
  • LLM Cost Optimization

    sickn33/agentic-awesome-skills

    Reduce LLM API and infrastructure costs through model selection, prompt caching, batching, caching, quantization, and self-hosting strategies.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    AI & LLM EngineeringAuto-check passed
  • LLM Gateway

    sickn33/agentic-awesome-skills

    Deploy an API gateway for LLM traffic with load balancing, rate limiting, key management, semantic caching, fallback routing, and cost tracking.

    47k GitHub starsUsed in 1 repo~2.1k tokens
    Backend & APIsAuto-check passed

More from OnlyTerp/prompt-cache-skills

All 13 skills in this repo
  • Aider 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.

    114 GitHub stars~990 tokensUpdated 1 mo ago
    Auto-check passed
  • 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.

    114 GitHub stars~638 tokensUpdated 1 mo ago
    Auto-check passed
  • Cline OpenAI Prompt Cache Key Fix

    OnlyTerp/prompt-cache-skills

    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.

    114 GitHub stars~868 tokensUpdated 1 mo ago
    Auto-check passed
  • 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.

    114 GitHub stars~751 tokensUpdated 1 mo ago
    Auto-check passed
  • Continue Enable Defaults

    OnlyTerp/prompt-cache-skills

    Continue's prompt caching is opt-in via config and off by default.

    114 GitHub stars~977 tokensUpdated 1 mo ago
    Auto-check passed
  • Continue Gemini Explicit

    OnlyTerp/prompt-cache-skills

    Continue's Gemini provider doesn't use the cachedContents API at all.

    114 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Cline Prompt Cache Ladder Check

What does Cline Prompt Cache Ladder Check do?

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. After Cline moved to a monorepo built on the Vercel AI SDK, this skill became a patch-and-verify guide for the cline/cline repository. Earlier versions called Cline's habit of marking recent user messages a copy-paste bug; later analysis showed it is a deliberate rolling read/write ladder, so the current advice is to verify it rather than rip it out.

When should I use Cline Prompt Cache Ladder Check?

Cline Prompt Cache Ladder Check fits situations like: auditing whether Cline's prompt caching behaves as intended on the wire; adding a cache breakpoint for tool definitions in Cline's Anthropic path; tuning the cache TTL for requests that go to Anthropic or an OpenAI-compatible relay.

How do I install Cline Prompt Cache Ladder Check in Claude Code?

Run `npx skills add OnlyTerp/prompt-cache-skills --skill cline-fix-volatile-msg -a claude-code`. Or copy the skill folder (skills/cline-fix-volatile-msg in OnlyTerp/prompt-cache-skills) into .claude/skills/cline-fix-volatile-msg in your project. Claude Code loads it when a task matches its description.

How do I install Cline Prompt Cache Ladder Check in Codex?

Run `npx skills add OnlyTerp/prompt-cache-skills --skill cline-fix-volatile-msg -a codex`. Or copy the skill folder (skills/cline-fix-volatile-msg in OnlyTerp/prompt-cache-skills) into .agents/skills/cline-fix-volatile-msg in your project. Codex loads it when a task matches its description.

Can I use Cline Prompt Cache Ladder Check 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-fix-volatile-msg -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-fix-volatile-msg, .gemini/skills/cline-fix-volatile-msg, .github/skills/cline-fix-volatile-msg and .opencode/skills/cline-fix-volatile-msg in your project.

What does Cline Prompt Cache Ladder Check need to run?

SKILL.md names no scripts, command-line tools or credentials: Cline Prompt Cache Ladder Check is instructions for the agent only. Our summary lists: A checkout of the cline/cline monorepo; A way to inspect the outgoing API requests.

Does Cline Prompt Cache Ladder Check 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 Prompt Cache Ladder Check 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 Prompt Cache Ladder Check use?

Cline Prompt Cache Ladder Check 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 Prompt Cache Ladder Check use?

About 2k tokens (SKILL.md is roughly 8.1k 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 Prompt Cache Ladder Check?

Skills that share tags, products or a category with Cline Prompt Cache Ladder Check: Dt Obs Genai (Dynatrace/dynatrace-for-ai, 161 stars), Prefix Cache Replay (benchflow-ai/skillsbench, 1.8k stars), Cache Credits Analyzer (TsinHzl/kiro2cc-proxy, 164 stars) and Prompt Caching (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cline Prompt Cache Ladder Check?

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.