Donna: Instructions file for Claude Code

CLAUDE.md

Donna CLAUDE.md is an instructions file for Claude Code from LegalQuants/Donna. It costs 3,770 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Donna, a SvelteKit web app that provides the user interface for a legal-AI backend. They explain the app’s architecture, repository layout, development tools, and verification steps.

In plain words
What is it for?
Use them when starting work on Donna, especially to understand how its frontend communicates with the legal-AI service, where files belong, and how to run and check changes.
Why use it?
They give coding agents and developers the project context needed to make changes consistently and avoid editing the backend or breaking the app’s design.

Instructions file for Claude Code

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

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd ../.. && npm run gen:api # regenerate types.

Reuse

Borrowing it

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

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 Donna CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/legalquants/donna/claude-md/github.svg)](https://agentmods.dev/instructions/legalquants/donna/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/legalquants/donna/claude-md"><img src="https://agentmods.dev/badge/instructions/legalquants/donna/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.

agentmods 80×15 button for Donna CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/legalquants/donna/claude-md"><img src="https://agentmods.dev/badge/instructions/legalquants/donna/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,770 This file is loaded in full into every session.
When invoked 3,770 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.03770 $0.03770
Opus 5 $0.01885 $0.01885
Sonnet 5 $0.00754 $0.00754
Haiku 4.5 $0.00377 $0.00377

Measured 10d ago against content hash d3d687a77a42, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Donna CLAUDE.md scanned grade A 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

it; raw `curl` doesn't, so a hand-forged `curl` login will 403/404. Test login via Playwright.
CLAUDE.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — engineering guide for Donna

This file orients a coding co-pilot — a human developer or another AI agent (Claude Code reads it automatically on session start) — so you can understand the whole project and pick up the roadmap from where it stands. Read it once, top to bottom, before your first change.

For what the product is and why, read docs/PRODUCT.md first. For how to run it, README.md. This file is how to build in it well.


1. What Donna is, in one breath

Donna is a standalone SvelteKit app — a friendly, document-forward frontend for the LQ.AI legal-AI backend. Donna implements no legal-AI logic itself: retrieval, the citation engine, anonymization, skills, playbooks, tabular review, and the autonomous runtime all live in lq-ai. Donna's job is to make that power usable, transparent, and controllable through a clean reading-first UI.

Donna talks to lq-ai only through its published API, and vendors that backend as a pinned git submodule (vendor/lq-ai) so the whole product runs from one compose file.

2. The cardinal rules (violate these and you'll break the project's model)

  1. Never edit vendor/lq-ai. It is a pinned submodule, not our code. If you need backend behavior that doesn't exist, that's an upstream request (§8), not a local patch.
  2. Consume the contract; never hand-fork it. API types are generated from lq-ai's OpenAPI into src/lib/api/backend.d.ts via npm run gen:api. Derive types from there. (Where the backend types a field loosely — additionalProperties — hand-type it in a small parser and say so in a comment; see the parseTabularResults / parseFindingList precedents.)
  3. The bar is green, not "no worse." npm run check = 0 errors / 0 warnings; npm run lint = prettier + eslint fully clean; the unit suite passes. Keep it that way.
  4. Merge PRs with a MERGE COMMIT. A squash would orphan the two one-time-format SHAs in .git-blame-ignore-revs. Never squash to main.
  5. Evidence before claims. "It works" requires a run you can point to — a passing test, a live e2e, an actual page load. Report failures faithfully.

Read the full file on GitHub · 231 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. 10d ago First seen · 231 lines · 3,770 tokens per session scan A d3d687a77a42

Subscribe to this mod's changes

Donna CLAUDE.md is an instructions file published in the GitHub repository LegalQuants/Donna (24 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,770 tokens to every session, about $0.0188 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

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

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 · 5,153 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

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

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

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