What is probe CLAUDE.md?

Project-specific instructions for AI coding assistants working on Probe, a local code-search tool written in Rust. They require tests for changes and describe commands for unit, integration, command-line, property-based, and language-server tests.

Use them when changing Probe's search code, Rust modules, command-line interface, or language-server behavior, and when running its test commands.

They make the required testing work explicit and ensure changes are checked across the relevant parts of the tool.

How probelabs/probe configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to probelabs/probe. 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/probelabs/probe/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/probelabs/probe

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/probelabs/probe/claude-md/github.svg)](https://agentmods.dev/instructions/probelabs/probe/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/probelabs/probe/claude-md"><img src="https://agentmods.dev/badge/instructions/probelabs/probe/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/probelabs/probe/claude-md"><img src="https://agentmods.dev/badge/instructions/probelabs/probe/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9,231 This file is loaded in full into every session.

When invoked 9,231 The same file — it is already loaded in full.

Security scan D 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.09231	$0.09231
Opus 5.5	$0.03692	$0.03692
Sonnet 5.5	$0.01846	$0.01846
Haiku 4.5	$0.00923	$0.00923

Measured 2mo ago against content hash d65f84fd974d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

probe CLAUDE.md scanned grade D with 2 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 2mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 700 ~/Library/Caches/probe/lsp/workspaces/

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/Library/Caches/probe/lsp/workspaces/*/cache.db

CLAUDE.md · 1,120 lines

How it starts

The opening of the file, as written. The whole thing — 1,120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with the probe codebase.

IMPORTANT: ALWAYS use code-search-agent to navigate the codebase and ask questions about it.

Project Overview

Probe is an AI-friendly, fully local, semantic code search tool built in Rust that combines ripgrep's speed with tree-sitter's AST parsing. It's designed to power AI coding assistants with precise, context-aware code search and extraction capabilities.

Development Guidelines

1. Testing Requirements

EVERY feature, bug fix, or change MUST include tests:

Unit tests for new functions/modules (in same file using #[cfg(test)])
Integration tests for cross-module functionality (in tests/ directory)
CLI tests for command-line interface changes
Property-based tests with proptest for complex logic
Test coverage for edge cases and error conditions

Before committing:

make test           # Run all tests
make test-unit      # Run unit tests only
make test-cli       # Run CLI tests
make test-property  # Run property-based tests

LSP Integration Testing:

# Run specific LSP tests with mock servers
cargo test -p lsp-daemon mock_lsp_server_test --lib -- --nocapture
cargo test -p lsp-daemon core_lsp_operation_tests --lib -- --nocapture
cargo test -p lsp-daemon lsp_symbol_resolution_tests --lib -- --nocapture

# Run all LSP-related integration tests
cargo test -p lsp-daemon --test "*lsp*" -- --nocapture

LSP Mock Server Infrastructure: The project includes comprehensive mock LSP servers for testing (lsp-daemon/tests/mock_lsp/):

4 Language Servers: rust-analyzer, pylsp, gopls, TypeScript server
Realistic Scenarios: Success, empty arrays, null responses, errors, timeouts, sequences
Full LSP Protocol: Call hierarchy, references, definitions, symbols, hover
Edge Case Testing: Validates proper handling of empty vs null responses
Database Integration: Tests actual persistence and caching of LSP data

Read the full file on GitHub · 1,120 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.

2mo ago First seen · 1,120 lines · 9,231 tokens per session scan D d65f84fd974d

Subscribe to this mod's changes

probe CLAUDE.md is an instructions file published in the GitHub repository probelabs/probe (736 stars, last pushed 9d ago), licensed Apache-2.0. It adds 9,231 tokens to every session, about $0.0369 per session on Opus 5.5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai ai-coder ast cli code-search search-engine

probe CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
probe CLAUDE.mdprobelabs/probe	Instructions file	736	9d ago	Apache-2.0	D	9,231	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

probe: Instructions file for Claude Code