What is milady AGENTS.md?

Project instructions stored in an AGENTS.md file for working on the milady-ai/milady codebase. They describe the project, commands, naming rules, and required visual checks for its web interface.

Use them when developing milady, especially when changing the cloud frontend, where desktop and mobile screenshots must be reviewed.

They give a coding agent the repository-specific rules it needs to make changes and verify them correctly.

How milady-ai/milady configures Codex and OpenCode

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/AGENTS.md

Clone the repo

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

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

Your own site

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

Per session 5,601 This file is loaded in full into every session.

When invoked 5,601 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	$0.05601	$0.05601
Opus 5.5	$0.02240	$0.02240
Sonnet 5.5	$0.01120	$0.01120
Haiku 4.5	$0.00560	$0.00560

Measured 2mo ago against content hash fd147d8f0a1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

milady 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 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.

AGENTS.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Milady — Project Codex Guidance

Milady is a local-first AI assistant built on elizaOS. It wraps the elizaOS runtime with a CLI, desktop app (Electrobun), web dashboard, and platform connectors (Telegram, Discord, WeChat, etc.). Inherits ~/.codex/AGENTS.md.

Cloud frontend visual review (REQUIRED for any UI change)

Any change in eliza/packages/cloud-frontend/ MUST go through the manual-review loop before being declared done. Automated tests catch what they assert; hover regressions, palette drift, broken empty states, and mobile layout breaks slip through. The harness produces evidence — you produce the verdicts.

How to run

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

This runs tests/e2e/aesthetic-audit.spec.ts headlessly across every route in src/App.tsx (53 routes × desktop + mobile × rest + hover ≈ 200 screenshots). The injected-ethereum login flow is wired into the spec so dashboard pages render their authed content; admin pages are dev-open via import.meta.env.DEV. Output lands in:

eliza/packages/cloud-frontend/aesthetic-audit-output/
  desktop/<slug>.png            rest screenshot
  desktop/<slug>--hover.png     hover state (primary button focused)
  mobile/<slug>.png
  mobile/<slug>--hover.png
  manual-review/<slug>.md       REQUIRED per-page verdict markdown
  contact-sheet.html            grid view of every shot + flagged issues
  report.json                   machine-readable audit data

Required loop (run 5+ iterations until every page hits verdict=good)

Run audit:cloud.
Open contact-sheet.html. Walk every page touched by your change (and every page reachable through transitive deps — header, footer, theme, buttons).
For each page, open manual-review/<slug>.md and fill in:
- Visual issues (anything that looks wrong or off-brand)
- Color / hover violations (orange→black or any blue is banned)
- Layout breaks (viewport + element)
- Interaction targets the e2e suite should cover
- Verdict: good · needs-work · needs-eyeball · broken
Fix the issues.
Commit screenshots + reviews + code together.
Re-run the audit. Repeat. Do not declare done until every page is good.

Read the full file on GitHub · 326 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 · 326 lines · 5,601 tokens per session scan A fd147d8f0a1a

Subscribe to this mod's changes

milady AGENTS.md is an instructions file published in the GitHub repository milady-ai/milady (356 stars, last pushed 22d ago), licensed MIT. It adds 5,601 tokens to every session, about $0.0224 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 Frontend agent agent-skills agents clawd clawdbot

milady AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
milady AGENTS.mdmilady-ai/milady	Instructions file	356	22d ago	MIT	A	5,601	Codex, OpenCode
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	today	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 Codex