FeaturesHow it worksIntegrationsPricingBlog GitHub

Stop sending mediocreprompts to your AI.

PrePrompt is the open-source MCP server that intercepts your prompts in Claude Code, Cursor, Windsurf and Zed — scores them in under a millisecond, and rewrites the bad ones before they hit the model.

claude-code · ~/projects/api
▎ your prompt
add tests
preprompt · score 64 · enrich
▎ rewrite
add unit tests for src/handlers/auth.py covering: valid token, expired token, missing token, and malformed bearer header. use pytest + the existing conftest.py fixtures. match the style in tests/test_billing.py.
✓ keptpreprompt-rate keep · 1.2s saved · sidecar 7b3f…
<1ms
classifier
3
routes
0
telemetry
MIT
license

Drops into the IDE you already use

02 — Features

A scoring system, a rewriter, and a dashboard. Nothing you have to think about.

Real-time classifier

Every prompt gets a score in under a millisecond. Nothing gets sent through the network until you've earned a rewrite.

Before / after diff

Every intercept shows the original and the rewrite side by side. Approve, revert, or move on with one keystroke.

~700ms overhead

The Haiku rewrite adds about 0.7 seconds to a complex prompt. Simple prompts pay zero — they never leave your machine.

Acceptance over time

Watch your accept-rate climb as the classifier learns your project. A real signal that the rewrites are actually working.

0%25%50%75%100%W1W2W3W4W5W6W7W871% ↑
03 — Workflow

Three steps. None of them yours.

Once you install, PrePrompt runs as a sidecar to your IDE. It only speaks up when a prompt is bad enough that a rewrite is the kindest thing to do.

01

Intercept

PrePrompt hooks into the UserPromptSubmit event your IDE already fires. Every prompt is intercepted locally, before a single byte leaves the machine.

claude-code → preprompt.hook("add tests")
02

Classify

A heuristic classifier scores intent, specificity, and project-context cues in under a millisecond. Simple prompts pass through. Vague ones route to a clarifier. Bad ones route to a rewriter.

score = 64 · route = enrich
03

Rewrite

Only complex prompts go to Claude Haiku — and only with the project context PrePrompt has already learned. The rewrite arrives in ~700 ms and goes straight into your IDE chat.

preprompt → claude_code("rewritten prompt …")
04 — Who it's for

Four people. Same four-word prompts. Same fix.

Solo dev

You ship features alone all day

The pain · Your prompts are 3 words because you know what you mean. The model doesn't.

The fix · PrePrompt fills in the missing 50 words from the files you're in. You stay in flow.

Staff engineer

You jump between four codebases

The pain · Context-switching means re-typing the same setup blurb to Claude five times a day.

The fix · Per-repo memory recalls each project's stack, patterns, and conventions. Automatic.

Founder / CTO

Your team shares an Anthropic bill

The pain · Half of every Haiku rewrite is wasted because the input prompt was vague.

The fix · Better intercepts mean fewer rewrite round-trips. Bill drops, output quality climbs.

Learning AI dev

You're newish to Claude Code

The pain · You don't yet know what makes a good prompt vs. a bad one — and the docs don't say.

The fix · Every intercept shows you the rewrite. PrePrompt is the world's quietest mentor.

05 — How we compare

The fastest way to send a bad prompt is to think you've already fixed it.

Four ways to handle prompt quality. Three of them require you to remember to do something.

PrePrompt
open · local
Type carefully
discipline-based
Prompt mgr SaaS
$$$ · hosted
Vendor sidecar
in-platform
Runs inside Claude Code / Cursor
Sub-millisecond classifier
Zero data leaves your machine by default
Per-project memory
One-click revert / accept
Open source (MIT)
Live dashboard with accept-rate
Costs $0 to start
supported partial not really
06 — Voices

What people stop saying once PrePrompt is on.

Half my prompts to Claude Code were three-word vibes. PrePrompt rewrites them with the files I'm in and the patterns from my last 50 prompts. I haven't said "add tests" in two months.

Anaya, staff engineer

Series B fintech, San Francisco

I thought I was a prompting pro. My own dashboard says my accept-rate doubled after switching on PrePrompt. The "before" version of me was guessing.

Marco, indie dev

Lisbon, ships side-projects

The thing that actually sold the team: it runs locally, no prompts ever hit a third-party log, and the only outbound call is the same Anthropic one our IDE already makes.

Priya, infra lead

200-engineer eng org

An honest dashboard for prompting. PrePrompt Replace your vibes with a real signal. Accept rate, route ratios, per-project memory — all in a local SQLite database you control.

Plug into the IDE you already use. Four supported today. MCP transport everywhere there's MCP. UserPromptSubmit hook where there's a hook.

C

Claude Code

First-class UserPromptSubmit hook. Zero config.

C

Cursor

Auto-attaches in Agent mode via MCP.

W

Windsurf

MCP transport — drop in the JSON, done.

Z

Zed

Lightweight MCP — terminal-fast.

07 — Privacy

Local-first isn't a tagline. It's the default behaviour.

We built PrePrompt for ourselves first. That means no analytics dashboards we don't own, no third-party log sink, no surprise data trail. If you flip telemetry on, you decide what gets sent and to whom.

Zero telemetry by default

Not a single event leaves your machine unless you flip a switch. The product ships off.

SQLite, on your laptop

Every prompt, every score, every rewrite lives at ~/.preprompt/history.db. You own it.

MIT, fully readable

Every line is on GitHub. Audit it, fork it, vendor it. No closed-source layer.

One outbound call

Only Anthropic — the same API your IDE already uses. We never proxy your code.

<1 ms

Classifier latency

~700 ms

Haiku rewrite p50

0 byte

Telemetry by default

"An IDE without PrePrompt is an IDE where the most expensive model in your stack is being prompted by someone in a hurry. PrePrompt is the slow-down step that ends up saving everyone time."

Yashdeep Tehlan

Author of PrePrompt · ex-DevTools

08 — In the wild

What the dashboard actually shows.

A peek at the local SQLite log. Every prompt, scored. Every rewrite, kept or reverted. Your prompts never leave this database — except the one round-trip to the model your IDE already uses.

Recent intercepts

localhost:7777 · last 4 prompts · auto-refreshes every 30s

TimeScoreRouteOriginalRewrite
12:0464enrichadd testsadd pytest unit tests for src/handlers/auth.py covering valid, expired and missing tokens. match tests/test_billing.py style.
12:018passfix this typo— passed through —
11:5871enrichrewrite the auth middlewarerefactor the JWT middleware in api/middleware/auth.ts to verify tokens locally via jose's `jwtVerify`, eliminate the per-request supabase RPC, and surface auth errors via the existing AppError type.
11:5324clarifywhat should we do?→ asked: about what? the failing migration, the open PR, or the perf regression?
Showing 4 rowsUpdated just now
09 — Install

One command. Then keep coding.

PrePrompt picks up your existing Anthropic key. New accounts get $5 free credit at the Anthropic console — enough for thousands of prompts.

pip install preprompt && preprompt install

works on macOS, Linux, Windows · python ≥ 3.10 · MIT licensed

10 — Pricing

Free forever for one developer. Hosted when you want it.

Hobby

$0forever

Everything PrePrompt does today. Open source. Bring your own Anthropic key.

  • Full classifier + rewriter
  • Local SQLite dashboard
  • Project-scoped memory
  • All 4 IDE integrations
  • Community support
Install free
popular

Dev

$14/month

Hosted rewriter endpoint. We hold the Anthropic key. You get one less thing to babysit.

  • Everything in Hobby
  • Hosted /v1/optimize endpoint
  • 30 enrichments / month included
  • Cloud dashboard
  • Email support
Coming soon

Pro

$29/month

For developers who live in their IDE. Unmetered, cross-machine memory, priority rewrites.

  • Everything in Dev
  • Unmetered enrichments
  • Cross-machine project memory
  • Priority routing — p50 < 400 ms
  • Direct founder support
Coming soon

Team tier in private beta. Email us.

11 — Questions

The eight we get the most.

No. The heuristic classifier runs in under 1ms locally with zero API calls. Simple prompts — questions, short acknowledgements, already-structured requests — pass through untouched. Only complex prompts scoring 38 or higher trigger a Claude Haiku rewrite, which adds approximately 700 milliseconds.
The only external call is to Anthropic's API to rewrite the prompt — the same API your IDE already uses. Your codebase, files, and history stay local in SQLite at ~/.preprompt/history.db. We have zero telemetry by default.
No. PrePrompt uses your Anthropic API key directly. New accounts get $5 free credit at console.anthropic.com — enough for thousands of prompts. This is completely separate from your Claude.ai Pro or Team subscription.
Claude Code (fully automatic via UserPromptSubmit hook), Cursor (automatic in Agent mode via MCP), Windsurf, and Zed. VS Code support is in active development.
MCP (Model Context Protocol) is an open standard from Anthropic that lets external tools speak to AI coding assistants. PrePrompt implements an MCP server that hooks into the UserPromptSubmit event, scores and (when needed) rewrites prompts before they reach the model.
Yes. The local dashboard at localhost:7777 shows a before/after diff for every rewritten prompt, with a one-click revert. Run `preprompt-rate keep` or `preprompt-rate revert` from your terminal to give explicit feedback.
PrePrompt detects the git remote of the directory each prompt is sent from and tags everything with that project ID. Stack memory (your frameworks, your file layout, your naming conventions) is stored per-project, so a prompt in your Django repo gets enriched with Django context — not the React context from your other repo.
Yes. MIT licensed at github.com/Preprompt-ai/preprompt. PRs welcome.
Ready when you are

Your next prompt could be thebest one this week.

PrePrompt installs in 30 seconds, sits silently in your IDE, and only speaks up when a rewrite would genuinely save you time.

free forever · MIT · pip install preprompt