Promptscout

promptscout

A CLI tool that enriches your coding agent prompts with codebase context using a local LLM. No API keys, no cloud. Runs on your machine.

**Designed as a Claude Code plugin.** It hooks into your prompt submission flow and adds codebase context before Claude sees it.

Motivation

When you ask a coding agent like Claude Code, Cursor, or Copilot to work on your codebase, the agent spends time and tokens discovering which files matter. It greps, reads, explores, all on your dime.

promptscout does that discovery locally, for free. A small local LLM reads your prompt, searches your codebase with `ripgrep` and `git`, and appends the results to your original prompt. The paid agent gets a prompt that already contains the relevant file paths, code snippets, and commit history. It can skip straight to the actual work.

Your original prompt is never modified. promptscout only appends context.

How It Works

flowchart LR
    A["Raw Prompt"] --> B["Local LLM
(Qwen 3 4B)"]
    B -->|"tool calls"| C["ripgrep / git"]
    C --> D["Original Prompt
+ Discovered Context"]

    subgraph B_ctx[" "]
        direction TB
        T["Project Tree
(git ls-files)"]
    end
    T -.->|"context"| B

1. You run promptscout "check the auth module, there might be a token refresh bug"
2. The local LLM sees your prompt along with the project file tree (git ls-files) and decides which search tools to call
3. The LLM outputs tool calls directly as JSON (e.g. file_finder("auth"), section_finder("token"), git_history("refresh"))
4. Each tool runs against your codebase using ripgrep and git
5. The output is your original prompt unchanged, followed by the discovered context
6. The result is copied to your clipboard, ready to paste into your coding agent

Installation

Prerequisit