Continue Fix Volatile Msg

Community

OnlyTerp

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.

Overview

Publisher	OnlyTerp
Repository	`prompt-cache-skills`
Skill name	`continue-fix-volatile-msg`
Stars	116
Forks	10
Bundled files	Instructions only
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by OnlyTerp on GitHub. Read the source before you install it.

Installation

Install the Continue Fix Volatile Msg AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/OnlyTerp/prompt-cache-skills/tree/main/skills/continue-fix-volatile-msg
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/OnlyTerp/prompt-cache-skills/tree/main/skills/continue-fix-volatile-msg

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/OnlyTerp/prompt-cache-skills.git /tmp/prompt-cache-skills
mkdir -p .claude/skills
cp -r /tmp/prompt-cache-skills/skills/continue-fix-volatile-msg .claude/skills/continue-fix-volatile-msg

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Continue Fix Volatile Msg in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Continue Fix Volatile Msg on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Continue Fix Volatile Msg is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Continue: the "volatile message" is a rolling ladder — verify, don't rip out

REANALYZED 2026-08-28. The previous version of this skill renamed addCacheControlToLastTwoUserMessages to a "last stable message" variant. Direct source recon shows Continue ships the same documented rolling read/write ladder as Cline/Roo (the helper name persists in packages/openai-adapters/src/apis/AnthropicUtils.ts). Applying the old diff would remove a working cache write point.

Target

packages/openai-adapters/src/apis/AnthropicUtils.ts (helper) and its callers in the Anthropic adapter; core/llm/llms/Bedrock.ts (_addCachingToLastTwoUserMessages, cachePoint shape) for the Bedrock path.

What Continue actually does

Same two-breakpoint ladder as Cline/Roo: current user turn = write point, previous user turn = read point. See cline-fix-volatile-msg for the full explanation and the 3-turn wire test. Continue's distinct problem is not the ladder — it's that caching is gated behind config and off by default, so most users get nothing at all, and no TTL extension exists for long sessions.

Step 1 — verify the ladder on the wire (before any change)

Same 3-turn capture as the Cline skill. Continue gates the whole caching path behind cacheBehavior config — if the capture shows zero cache fields in the request at all, fix the config first (next step) and re-capture before judging the ladder.

Step 2 — default-on (the actual money fix)

Continue's cacheBehavior config defaults leave Anthropic caching off for most installs. See continue-enable-defaults — that skill remains the primary win for this harness. The ladder should be verified after defaults are on, never instead.

Step 3 — Bedrock path: verify the cachePoint translation

Continue's Bedrock adapter re-implements caching with cachePoint (not cache_control — gotcha 12). Two checks before trusting it:

The cachePoint placement mirrors the ladder (write point on the current turn, read point on the previous) — same 3-turn wire test through the Bedrock envelope, reading cacheReadInputTokenCount/cacheWriteInputTokenCount.
The Bedrock model ID in use actually supports cache points (gotcha 13 — the AWS support matrix drifts; verify, don't assume).

Verify (whole skill)

After default-on: request bodies contain cache_control on the ladder positions; 3-turn capture shows the write@N → read@N+1 pattern; Bedrock capture shows the same through cachePoint.

Background

docs/gotchas.md #12 (cachePoint), #17 (relay field-stripping), #18 (the ladder test).
Full audit: audits/continue.md.

Frequently asked questions

What does the Continue Fix Volatile Msg AI skill do?

Ladder-aware Continue Anthropic caching — verify the rolling ladder on the wire, then enable it by default and add TTL coverage.

Why use Continue Fix Volatile Msg on TypingMind?

Because you install it once and use it with any model. Continue Fix Volatile Msg is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Continue Fix Volatile Msg in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/OnlyTerp/prompt-cache-skills/tree/main/skills/continue-fix-volatile-msg. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Continue Fix Volatile Msg?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Continue Fix Volatile Msg?

As many as you like. As long as a model supports skills, you can use Continue Fix Volatile Msg with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Continue Fix Volatile Msg AI skill free?

It is published on GitHub by OnlyTerp. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Openclaw Changelog Update

openclaw

OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

Openclaw Ci Limits

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

Openclaw Debugging

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

Openclaw Live Updater

openclaw

OrganizationPopular

Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation. Use for fast-forward update…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Continue: the "volatile message" is a rolling ladder — verify, don't rip out

Target

What Continue actually does

Step 1 — verify the ladder on the wire (before any change)

Step 2 — default-on (the actual money fix)

Step 3 — Bedrock path: verify the cachePoint translation

Verify (whole skill)

Background

Frequently asked questions

Related AI Skills

Set up your own AI workspace now