prompte-mcp: Instructions file for Claude Code

CLAUDE.md

prompte-mcp CLAUDE.md is an instructions file for Claude Code from AlanRoybal/prompte-mcp. It costs 504 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for using the Prompte MCP server, a prompt-improvement assistant. It defines when to ask the assistant to improve a request and how to handle its result.

In plain words
What is it for?
For deciding when to call the enhance_prompt tool and whether to show or silently apply its suggested prompt.
Why use it?
It gives Claude Code a consistent way to improve prompts for tasks such as debugging, analysis, coding, architecture, and review.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is AlanRoybal/prompte-mcp's own configuration. It tells Claude Code how to work on prompte-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 prompte-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AlanRoybal/prompte-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/AlanRoybal/prompte-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AlanRoybal/prompte-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 prompte-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alanroybal/prompte-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/alanroybal/prompte-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/alanroybal/prompte-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/alanroybal/prompte-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 prompte-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/alanroybal/prompte-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/alanroybal/prompte-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 504 This file is loaded in full into every session.
When invoked 504 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 $0.00504 $0.00504
Opus 5 $0.00252 $0.00252
Sonnet 5 $0.00101 $0.00101
Haiku 4.5 $0.00050 $0.00050

Measured 8d ago against content hash 9e3f5c1d95c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prompte-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 8d 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 · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompte MCP

You have access to a prompt engineering assistant via the prompte MCP server.

When to call enhance_prompt

Call it automatically — before formulating your response — when the user's message involves:

  • Debugging: error messages, crashes, "why does X fail", stack traces
  • Reasoning: trade-offs, analysis, "think through", algorithm evaluation
  • Generation: writing code, functions, classes, APIs, scripts
  • Architecture: system design, data models, infrastructure decisions
  • Review: code review, auditing, checking correctness

Do not call it for: simple factual questions, conversational messages, or prompts that already contain explicit reasoning instructions. If bypassed: true is returned, respond normally without applying any technique.

What to do with the result

Call enhance_prompt({ prompt: "<user's message>" }). Then:

If autoAccept is false (default) — show and ask

Present the enhancement to the user and wait for their decision before answering:

I've selected the **{technique.name}** technique for this ({intent}).

**Original:** {original}

**Enhanced:** {enhanced}

[A] Accept – I'll answer using this enhanced prompt
[E] Edit – paste a revised version and I'll use that
[S] Skip – I'll answer using your original prompt
[Q] Quit – cancel, don't answer
  • If they say accept (or just "yes", "go ahead", "a", etc.) → answer using techniqueInstruction
  • If they paste an edit → use their version as the prompt and answer it
  • If they say skip (or "s", "no", "original") → answer their original prompt without any technique
  • If they say quit (or "q", "cancel", "stop") → stop and do nothing

If autoAccept is true — apply silently

Skip showing the diff. Apply techniqueInstruction directly when composing your response. Do not mention Prompte or the technique to the user.

Check autoAccept by calling get_config once per session (cache the result).

Feedback

After responding, call record_feedback({ technique: "<id>", helpful: true/false }) if you can judge whether the technique genuinely improved your answer. Skip this if uncertain.

Read the full file on GitHub · 56 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. 8d ago First seen · 56 lines · 504 tokens per session scan A 9e3f5c1d95c6

Subscribe to this mod's changes

prompte-mcp CLAUDE.md is an instructions file published in the GitHub repository AlanRoybal/prompte-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 504 tokens to every session, about $0.0025 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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens