What is julie AGENTS.md?

A development guide for Julie, a cross-platform Rust server that helps coding tools search, navigate, and edit code across 36 programming languages.

Use it when developing Julie, its language support, search and storage systems, or its MCP connection over standard input and output.

It explains the project's architecture and operating rules, reducing mistakes when working on its code intelligence features or server behavior.

julie AGENTS.md — Instructions file for Codex and OpenCode by anortham: A development guide for Julie, a cross-platform Rust server…

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/anortham/julie/agents-md

Clone the repo

git clone --depth 1 https://github.com/anortham/julie

Made for: Codex, OpenCode.

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/anortham/julie/agents-md.svg)](https://agentmods.dev/instructions/anortham/julie/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/anortham/julie/agents-md"><img src="https://agentmods.dev/badge/instructions/anortham/julie/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 8,626 This file is loaded in full into every session.

When invoked 8,626 The same file — it is already loaded in full.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.08626	$0.08626
Opus 5	$0.04313	$0.04313
Sonnet 5	$0.01725	$0.01725
Haiku 4.5	$0.00863	$0.00863

Measured 5d ago against content hash 35b877d3f3a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

julie AGENTS.md scanned grade B with 1 finding 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 5d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **One-time setup**: `cargo build --release && cargo xtask dev-link` — replaces the bundled `julie-server` inside `~/.claude/plugins/cache/julie-plugin/julie/<v>/bin/<arch>/` with a symlink to `target/release/julie-serv

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

julie CLAUDE.md — 100% identical, 0 lines differ

AGENTS.md · 532 lines

How it starts

The opening of the file, as written. The whole thing — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Julie — Development Guidelines

All AI coding agents (Claude Code, Copilot, Cursor, Windsurf, Cody, Gemini CLI, aider, etc.) must follow these guidelines.

Project Overview

Julie is a cross-platform code intelligence server built in Rust. LSP-quality features across 36 languages via tree-sitter, Tantivy full-text search, and instant search availability.

Key Project Facts

Language: Rust (native performance, cross-platform)
Purpose: Code intelligence MCP server (search, navigation, editing)
Architecture: Tantivy full-text search + SQLite structured storage + KNN vector search (embeddings)
Mode: Stdio MCP server (JSON-RPC over stdin/stdout). The no-args julie-server serves in-process over rmcp stdio, leader-locked per workspace. There is no forked daemon, stdio adapter, HTTP MCP bridge, or julie daemon runtime.
Origin: Native Rust implementation for true cross-platform compatibility
Crown Jewels: 36 tree-sitter extractors with comprehensive test suites, now maintained in the external anortham/julie-extractors repo and consumed here as a pinned git dependency

🏆 Current Language Support (36 - Complete)

The 36 extractors live upstream in anortham/julie-extractors (consumed as a pinned git dep). Language and parser work — adding languages, upgrading parsers, golden fixtures, capability tests — happens there. Re-pin julie's julie-extractors git-dep in Cargo.toml and sync SEMANTIC_INDEX_ENGINE_VERSION (in src/tools/workspace/indexing/engine_version.rs) to the new tag's EXTRACTION_CONTRACT_VERSION to pick up a new release.

Core Languages: Rust, TypeScript, JavaScript, Python, Java, C#, VB.NET, PHP, Ruby, Swift, Kotlin, Scala Systems Languages: C, C++, Go, Lua, Zig Functional: Elixir, Erlang Specialized: GDScript, Vue, Razor, QML, R, SQL, HTML, CSS, Regex, Bash, PowerShell, Dart Documentation: Markdown, JSON, TOML, YAML, XML

Read the full file on GitHub · 532 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.

5d ago First seen · 532 lines · 8,626 tokens per session scan B 35b877d3f3a0

Subscribe to this mod's changes

julie AGENTS.md is an instructions file published in the GitHub repository anortham/julie (6 stars, last pushed 16d ago), licensed MIT. It adds 8,626 tokens to every session, about $0.0431 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

julie AGENTS.md