codexia: Instructions file for Codex

AGENTS.md

codexia AGENTS.md is an instructions file for Codex, OpenCode from milisp/codexia. It costs 1,658 tokens per session, scanned A, original, MIT.

Project-specific instructions for agents working on Milisp or Codexia, including its tools, technologies, file structure, and common commands.

In plain words
What is it for?
They guide work in a React, TypeScript, Tailwind, shadcn, Zustand, and Tauri project, including which checks and commands to use for frontend or Rust changes.
Why use it?
They give coding agents the local conventions needed to make compatible changes and avoid known project mistakes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is milisp/codexia's own configuration. It tells Codex and OpenCode how to work on codexia 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 codexia configures →

Reuse

Borrowing it

Nothing to install: this file belongs to milisp/codexia. 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/milisp/codexia/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/milisp/codexia

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.

agentmods badge for codexia AGENTS.md

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

agentmods 80×15 button for codexia AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/milisp/codexia/agents-md"><img src="https://agentmods.dev/badge/instructions/milisp/codexia/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,658 This file is loaded in full into every session.
When invoked 1,658 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01658 $0.01658
Opus 5.5 $0.00663 $0.00663
Sonnet 5.5 $0.00332 $0.00332
Haiku 4.5 $0.00166 $0.00166

Measured 20d ago against content hash 3615aae8b741, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codexia 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 20d 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 · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project Info

  • Agent os for codex cli and claude code cli - agent
  • use codex app-server and claude-agent-sdk-rs to connect Codexia

Project tech

  • Package manager: bun
  • Framework: React + shadcn + tailwindcss + TypeScript + Tauri v2
  • Don't use emit_all
  • UI: use shadcn UI components first, Button, Input, etc.
  • code comment language: English-only
  • Zustand: for state management with persistence
  • Don't break Fast Refresh: a .tsx file rendering UI must only export PascalCase components (no lowercase JSX-returning helpers), otherwise HMR falls back to a full page reload and drops in-flight events

Product UI

  • Build a product interface, not an inline documentation page. Make the user's task and primary action obvious before adding explanatory copy.
  • Keep default views concise: clear labels, controls, and compact status indicators. Add helper text only when it changes the user's immediate decision or prevents a likely mistake.
  • Use progressive disclosure for technical details: help popovers, expandable advanced settings, or linked documentation. Keep configuration paths, protocol terminology, implementation details, and long compatibility or security explanations out of the default view unless needed for the current task.
  • Show actionable errors and permission requirements when relevant, close to the affected control. Do not repeat generic warnings throughout a panel or present a saved configuration as a verified connection.
  • Use recognizable app or service icons with short names for selection lists. Icon-only actions need accessible labels and tooltips; unfamiliar concepts still need visible labels.
  • Present supported capabilities clearly. A few presets must not make a general integration feature look limited to those providers; keep adding custom integrations easy to discover.
  • Before finishing a UI change, review the default view: remove repeated explanations, move reference material into help, and check that the next action is clear without reading paragraphs.

Read the full file on GitHub · 103 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. 20d ago Changed · +2 lines · +101 tokens per session 3615aae8b741
  2. 22d ago Changed · +1 lines · +8 tokens per session 074f365facd0
  3. 1mo ago Changed · +18 lines · +529 tokens per session 3295fa11b645
  4. 1mo ago Changed · +15 lines · +364 tokens per session 9f3193475e57
  5. 1mo ago Changed c0b9bcd6fee0
  6. 2mo ago First seen · 67 lines · 656 tokens per session scan A ebd435a018f0

Subscribe to this mod's changes

codexia AGENTS.md is an instructions file published in the GitHub repository milisp/codexia (941 stars, last pushed 15d ago), licensed MIT. It adds 1,658 tokens to every session, about $0.0066 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.

Related

codexia AGENTS.md compared with instructions from other repositories

codexia AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
codexia AGENTS.mdmilisp/codexiaInstructions file94115d agoMITA1,658Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode