magector: Instructions file for Claude Code

CLAUDE.md

magector CLAUDE.md is an instructions file for Claude Code from krejcif/magector. It costs 1,553 tokens per session, scanned A, original, MIT.

Repository instructions for Magector, a tool that searches Magento 2 and Adobe Commerce code by meaning rather than exact words. They explain its Node.js and Rust parts, build commands, and tests.

In plain words
What is it for?
Building the Rust component, running MCP server tests, checking search accuracy, validating the project, and measuring performance.
Why use it?
They give the coding agent the project context and the correct commands for building and checking changes. This reduces guesswork when working on the search engine.

Instructions file for Claude Code

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

This is krejcif/magector's own configuration. It tells Claude Code how to work on magector 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 magector configures →

Reuse

Borrowing it

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

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 magector CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/krejcif/magector/claude-md.svg)](https://agentmods.dev/instructions/krejcif/magector/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/krejcif/magector/claude-md"><img src="https://agentmods.dev/badge/instructions/krejcif/magector/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,553 This file is loaded in full into every session.
When invoked 1,553 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 $0.01553 $0.01553
Opus 5 $0.00776 $0.00776
Sonnet 5 $0.00311 $0.00311
Haiku 4.5 $0.00155 $0.00155

Measured 7d ago against content hash 4438cd34b985, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

magector 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 7d 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 · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 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 code in this repository.

What This Is

Magector is a semantic code search engine for Magento 2 & Adobe Commerce. It uses a hybrid Node.js + Rust architecture: a thin Node.js layer (CLI + MCP server) delegates all indexing and search to a Rust binary (magector-core) that generates ONNX embeddings and searches an HNSW vector index.

Commands

Building

cd rust-core && cargo build --release   # Build Rust binary → rust-core/target/release/magector-core

No Node.js build step — src/ is plain ES modules.

Testing

npm test                          # MCP server integration tests (stdio JSON-RPC)
npm run test:no-index             # Skip tools requiring an index
npm run test:accuracy             # 101 E2E queries against Magento 2.4.7 ground truth
npm run test:accuracy:verbose     # Per-query accuracy metrics
npm run validate                  # Full validation suite (downloads Magento 2.4.7 if needed)
npm run benchmark                 # Performance benchmarks (latency, throughput)

Rust tests: cd rust-core && cargo test (557 unit tests in validation.rs).

Tests use no framework — direct Node.js scripts spawning the MCP server via stdio and validating JSON-RPC responses.

Running Locally

npx magector init /path/to/magento2    # Full setup: index + IDE config
npx magector search "product price"    # Search indexed code
npx magector stats                     # Show index statistics
npx magector mcp                       # Start MCP server

The CLI auto-detects the local Rust build at rust-core/target/release/magector-core.

Releasing

The release is triggered by pushing a v* tag to GitHub. The CI workflow (.github/workflows/release.yml) builds all platform binaries and publishes to npm.

Before releasing:

  1. Update README.md to reflect any new or changed MCP tools, CLI commands, or features added since the last release. The README is user-facing documentation and must stay in sync with the actual tool set in src/mcp-server.js.
  2. Update CHANGELOG.md with a new section for the version being released. Follow the Keep a Changelog format using Added, Changed, Fixed, and Removed subsections. Describe user-visible changes only — not internal refactors or CI tweaks unless they affect behavior.

Read the full file on GitHub · 133 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. 7d ago First seen · 133 lines · 1,553 tokens per session scan A 4438cd34b985

Subscribe to this mod's changes

magector CLAUDE.md is an instructions file published in the GitHub repository krejcif/magector (20 stars, last pushed 3d ago), licensed MIT. It adds 1,553 tokens to every session, about $0.0078 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 2026-08-30.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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