What is milady CLAUDE.md?

Project instructions for Claude Code when working on milady-ai/milady, a local-first AI assistant with a command line tool, desktop app, web dashboard, and platform connections.

Use them when changing milady code, especially its cloud frontend or shared packages that affect the frontend.

They record the repository's conventions, development commands, naming rules, and required visual review process.

How milady-ai/milady configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to milady-ai/milady. 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/milady-ai/milady/develop/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/milady-ai/milady

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/milady-ai/milady/claude-md/github.svg)](https://agentmods.dev/instructions/milady-ai/milady/claude-md)

Your own site

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

Per session 8,242 This file is loaded in full into every session.

When invoked 8,242 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.

Model	Per session	Once invoked
Fable 5.1	$0.08242	$0.08242
Opus 5.5	$0.03297	$0.03297
Sonnet 5.5	$0.01648	$0.01648
Haiku 4.5	$0.00824	$0.00824

Measured 2mo ago against content hash c687894547d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

milady 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 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.

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 · 668 lines

How it starts

The opening of the file, as written. The whole thing — 668 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Milady — Agent Conventions

Local-first AI assistant on elizaOS. CLI + desktop (Electrobun) + web dashboard + connectors.

Architecture commandments, QA protocol, git workflow: AGENTS.md. Sandbox/distribution: docs/sandbox-mode.md.

Naming

Write elizaOS (not ElizaOS). npm scope @elizaos/*. Plain language: Eliza agents. Exception: Eliza Classic plugin keeps Eliza (the 1966 chatbot).

Cloud frontend visual review (REQUIRED for any UI change)

Path/mode note: cloud-frontend lives at eliza/packages/cloud-frontend and is on disk only in local mode (bun run eliza:local). Every packages/cloud-frontend/… path in this section is relative to eliza/packages/cloud-frontend/.

For ANY change in eliza/packages/cloud-frontend/ (or any shared package whose UI bleeds into cloud-frontend), follow this loop until every touched page reaches verdict good:

bun run --cwd eliza/packages/cloud-frontend audit:cloud

This boots the dev server, performs an injected-ethereum login (synthetic JWT in localStorage.steward_session_token), visits every route in src/App.tsx at desktop + mobile, captures rest + hover screenshots, and writes:

packages/cloud-frontend/aesthetic-audit-output/
  desktop/<slug>.png            rest screenshot
  desktop/<slug>--hover.png     primary-button hover state
  mobile/<slug>.png
  mobile/<slug>--hover.png
  manual-review/<slug>.md       REQUIRED per-page verdict markdown (auto-stubbed)
  contact-sheet.html            grid index
  report.json                   machine-readable findings

The 5-loop grind:

Run the audit.
Open contact-sheet.html. Walk every affected page.
Fill in the verdict in manual-review/<slug>.md: visual issues, color/hover violations, layout breaks, e2e gaps, good · needs-work · needs-eyeball · broken.
Fix issues in source.
Commit screenshots + reviews + fixes together.
Re-run. Repeat until every page is good. Five loops is the floor for any meaningful redesign.

Read the full file on GitHub · 668 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 · 668 lines · 8,242 tokens per session scan A c687894547d5

Subscribe to this mod's changes

milady CLAUDE.md is an instructions file published in the GitHub repository milady-ai/milady (356 stars, last pushed 22d ago), licensed MIT. It adds 8,242 tokens to every session, about $0.0330 per session on Opus 5.5. 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.

Autonomous Agents agent agent-skills agents clawd clawdbot

milady CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
milady CLAUDE.mdmilady-ai/milady	Instructions file	356	22d ago	MIT	A	8,242	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	today	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

milady: Instructions file for Claude Code