Cline Pin Timestamp logo

Cline Pin Timestamp

Community
OnlyTerp
cline-pin-timestamp

Cline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.

Overview

PublisherOnlyTerp
Repositoryprompt-cache-skills
Skill namecline-pin-timestamp
Stars
116
Forks
10
Bundled files
Instructions only
Links
  • 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 Cline Pin Timestamp AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/OnlyTerp/prompt-cache-skills/tree/main/skills/cline-pin-timestamp
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/cline-pin-timestamp .claude/skills/cline-pin-timestamp
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cline Pin Timestamp 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 Cline Pin Timestamp 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 Cline Pin Timestamp 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.

Cline: pin the system-prompt timestamp

Target

src/core/prompts/system.ts in cline/cline. PR #1168 added a current-time field to the system prompt.

Symptom

The system prompt includes the current time. If the time is computed per-request (e.g. new Date().toISOString() evaluated at every call site), then the system prompt bytes differ on every request, which invalidates the system-prompt cache breakpoint. The cache write premium gets paid every turn for zero reads, on what's usually the largest single block in the prefix.

PR #1168 was merged despite a reviewer flagging exactly this:

"Just be aware that if the time is being calculated every time the user sends a request, it invalidates Anthropic's cache."

Verify on the wire: if the system text changes between consecutive calls in the same task, this bug is present.

Fix

Compute the timestamp ONCE at task start, store it on the task, pass through to every system prompt build:

diff
--- a/src/core/prompts/system.ts
+++ b/src/core/prompts/system.ts
@@
-export const SYSTEM_PROMPT = (...args) => `
-  ...
-  Current time: ${new Date().toISOString()}
-  ...
-`
+export const SYSTEM_PROMPT = (args: SystemPromptArgs) => `
+  ...
+  Current time: ${args.taskStartedAt}
+  ...
+`

Then in the task initialization code:

diff
+  this.taskStartedAt = new Date().toISOString()

And pass this.taskStartedAt everywhere SYSTEM_PROMPT is built.

If date awareness is critical for the agent and you want it to drift during a long session, round to the nearest day or hour rather than the second — that bounds the cache invalidation rate.

Verify

  1. Start mitmproxy.
  2. Run a Cline task. Wait 10 seconds. Send a second prompt in the same task.
  3. Diff the system prompt bytes between the two requests.
    • Before fix: bytes differ (timestamp incremented)
    • After fix: bytes identical
  4. Confirm response usage.cache_read_input_tokens covers the system prompt on turn 2.

Background

Anthropic caches the entire prefix UP TO AND INCLUDING the breakpoint. A single byte change before or at the breakpoint invalidates everything. Timestamps are the most common cache killer because they look innocent and few people think to check.

OpenAI's automatic prefix caching has the same vulnerability — same fix applies if Cline targets OpenAI as well.

See docs/gotchas.md #5 (byte-identity of tool definitions, same principle for system prompts) and #7 (OpenAI byte-identical prefix requirement).

Full audit: audits/cline.md.

Frequently asked questions

What does the Cline Pin Timestamp AI skill do?

Cline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.

Why use Cline Pin Timestamp on TypingMind?

Because you install it once and use it with any model. Cline Pin Timestamp 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 Cline Pin Timestamp in TypingMind?

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

Which AI models can use Cline Pin Timestamp?

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 Cline Pin Timestamp?

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

Is the Cline Pin Timestamp 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇