prompt-lab-mcp: Instructions file for Claude Code

CLAUDE.md

prompt-lab-mcp CLAUDE.md is an instructions file for Claude Code from jurek-f/prompt-lab-mcp. It costs 3,552 tokens per session, scanned A, original, MIT.

Instructions for an MCP server that connects a Prompt Lab web interface to an AI agent running prompt-optimization tests. It stores prompts, test cases, results, and suggestions, while the agent performs the language-model work.

In plain words
What is it for?
Use it when operating the Prompt Lab workspace, scanning its templates, or deciding whether saved test material should be loaded into the UI.
Why use it?
It enforces a startup routine and requires confirmation before test templates or system-prompt templates are sent to the web interface.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is jurek-f/prompt-lab-mcp's own configuration. It tells Claude Code how to work on prompt-lab-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything prompt-lab-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jurek-f/prompt-lab-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jurek-f/prompt-lab-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jurek-f/prompt-lab-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prompt-lab-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jurek-f/prompt-lab-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/jurek-f/prompt-lab-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jurek-f/prompt-lab-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jurek-f/prompt-lab-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prompt-lab-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jurek-f/prompt-lab-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jurek-f/prompt-lab-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,552 This file is loaded in full into every session.
When invoked 3,552 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.03552 $0.03552
Opus 5 $0.01776 $0.01776
Sonnet 5 $0.00710 $0.00710
Haiku 4.5 $0.00355 $0.00355

Measured 10d ago against content hash 522861501bac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prompt-lab-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 332 lines

How it starts

The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent instructions

What this server is

overhang-mcp is a lightweight broker that connects the Prompt Lab web UI to a Claude Code agent running prompt optimisation loops. It holds workspace state (system prompt, test cases, results, suggestions) and exposes it via HTTP (to the UI) and MCP (to the agent).

No LLM calls happen here. The agent (you) owns all LLM work.


Session startup — do this first

MANDATORY. Do not skip. Do not defer. Do not wait to be reminded.

Step 1 — Scan for templates (ALWAYS, no exceptions)

Run these two commands immediately at the start of every session:

ls prompt-lab/templates/
ls prompt-lab/system-prompts/

Even if you think there are no templates, run the commands. Even if you were just connected and think you already know the state, run the commands.

Step 2 — If files exist, ALWAYS ask before pushing to the UI

If you find any .json files in prompt-lab/templates/ or .txt files in prompt-lab/system-prompts/, STOP and ask the user:

"I found N test suite template(s): [list names] and M system prompt template(s): [list names]. Should I push all of them to the UI?"

Do NOT push anything without asking first. Pushing takes time — wait for confirmation.

Step 3 — If user says yes, push ALL of them to the UI

Push every file — not just the one the user wants to work with. All of them.

Test suite templates — for every .json file:

save_template(name=<file.name field or filename without extension>, testCases=<file.testCases>)

System prompt templates — for every .txt file:

save_system_prompt_template(name=<filename without extension>, content=<file contents>)

Call save_template / save_system_prompt_template once per file. All pushed templates appear in the UI dropdowns. The question of which one to work with comes after pushing, not instead of it.

After pushing, confirm: "Pushed N test suite(s) and M system prompt template(s) to the UI — all visible in the dropdowns."

Read the full file on GitHub · 332 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 332 lines · 3,552 tokens per session scan A 522861501bac

Subscribe to this mod's changes

prompt-lab-mcp CLAUDE.md is an instructions file published in the GitHub repository jurek-f/prompt-lab-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 3,552 tokens to every session, about $0.0178 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens