mgrep AGENTS.md

Repository instructions for mgrep, a TypeScript command-line tool that searches code, documents, images, and other files by meaning instead of only matching exact text. It also connects this search to coding agents and web search.

In plain words
What is it for?
Changing the command-line interface, semantic search, file indexing, coding-agent integrations, web search, tests, and TypeScript tooling.
Why use it?
They explain the project's purpose and development setup so agents can make changes that fit its search and integration model.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/mixedbread-ai/mgrep/agents-md
Clone the repo
git clone --depth 1 https://github.com/mixedbread-ai/mgrep

Made for: Codex, OpenCode.

Per session 1,917 This file is loaded in full into every session.
When invoked 1,917 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01917 $0.01917
Opus 5 $0.00958 $0.00958
Sonnet 5 $0.00383 $0.00383
Haiku 4.5 $0.00192 $0.00192

Measured 2d ago against content hash aedaed942d07, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mgrep AGENTS.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 2d 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.

AGENTS.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides context and guidelines for AI coding agents working on the mgrep codebase. It follows the AGENT.md specification and incorporates best practices from Anthropic, OpenAI, and Google.

Project Overview

mgrep is a semantic search CLI tool that brings natural language understanding to code search. It's built with TypeScript and designed to work seamlessly with AI coding agents.

Core Purpose

  • Replace pattern-based grep with semantic, natural-language search
  • Index and search code, PDFs, images, and text files
  • Integrate with coding agents (Claude Code, Codex, OpenCode, Factory Droid)
  • Provide web search capabilities alongside local file search

Tech Stack

  • Runtime: Node.js (ESM modules)
  • Language: TypeScript 5.x with strict mode
  • Package Manager: pnpm
  • Linting/Formatting: Biome
  • Testing: bats (Bash Automated Testing System)
  • API: Mixedbread SDK for semantic search

Project Structure

mgrep/
├── src/
│   ├── index.ts              # CLI entry point, command registration
│   ├── commands/             # CLI command implementations
│   │   ├── login.ts          # Authentication flow
│   │   ├── logout.ts         # Session cleanup
│   │   ├── search.ts         # Core search functionality
│   │   ├── switch-org.ts     # Organization switching
│   │   ├── watch.ts          # File watching and indexing
│   │   └── watch_mcp.ts      # MCP (Model Context Protocol) watch
│   ├── install/              # Agent integration installers
│   │   ├── claude-code.ts    # Claude Code integration
│   │   ├── codex.ts          # Codex integration
│   │   ├── droid.ts          # Factory Droid integration
│   │   └── opencode.ts       # OpenCode integration
│   └── lib/                  # Shared utilities and core logic
│       ├── auth.ts           # Authentication utilities
│       ├── config.ts         # Configuration management
│       ├── context.ts        # Execution context
│       ├── file.ts           # File operations
│       ├── git.ts            # Git integration
│       ├── logger.ts         # Logging utilities
│       ├── organizations.ts  # Organization management
│       ├── store.ts          # Mixedbread store operations
│       ├── sync-helpers.ts   # Synchronization utilities
│       ├── token.ts          # Token management
│       ├── utils.ts          # General utilities
│       └── warning.ts        # Warning display utilities
├── test/
│   ├── test.bats             # Integration tests
│   └── assets/               # Test fixtures
├── plugins/                  # Plugin definitions
├── guides/                   # Documentation guides
└── .claude-plugin/           # Claude Code plugin config

Read the full file on GitHub · 269 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. 2d ago First seen · 269 lines · 1,917 tokens per session scan A aedaed942d07

Subscribe to this mod's changes

mgrep AGENTS.md is an instructions file published in the GitHub repository mixedbread-ai/mgrep (4,389 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,917 tokens to every session, about $0.0096 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

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

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

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

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 · 4,345 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

next.js 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