agentmods.dev

codex-multi-profile AGENTS.md

Repository instructions for a Windows-only helper that manages multiple Codex Desktop accounts, including its PowerShell interface and launch behavior.

In plain words
What is it for?
Use them when editing account management, PowerShell scripts, startup behavior, routing, configuration, or tests in this project.
Why use it?
They prevent changes that could break account switching, configuration files, security rules, or the required Windows launch process.

Instructions file for CodexOpenCode

93 12d ago A scan 227 tokens original MIT
View the source file Hung2124/codex-multi-profile
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/hung2124/codex-multi-profile/agents-md
Clone the repo
git clone --depth 1 https://github.com/Hung2124/codex-multi-profile

Made for: Codex, OpenCode.

Per session 227 This file is loaded in full into every session.
When invoked 227 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00227 $0.00227
Opus 5 $0.00113 $0.00113
Sonnet 5 $0.00045 $0.00045
Haiku 4.5 $0.00023 $0.00023

Measured 2d ago against content hash 2c656ccd0185, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-multi-profile 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 2d 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 · 16 lines

What it actually says

AGENTS.md

This repository is a Windows-only Codex Desktop multi-account helper.

  • Read SKILL.md before changing launch behavior.

  • Never commit auth.json, backups, or launch-trace.log.

  • Do not replace the .cmd env wrapper with Start-Process alone.

  • Write config.toml without a UTF-8 BOM.

  • Run tests/Run-All.ps1 after script edits.

  • Router (pool / stick / route / depleted) is opt-in and must stay one-window AuthSwap. Do not add a mux or ChatGPT.exe patcher.

  • Layer and ChatGPT Web models stay off by default.

  • Humans pick accounts in Show-CodexAccountApp.ps1 (Codex Accounts). Do not treat PowerShell route as the product UI.

  • The account app must stay PowerShell 5.1 WPF (no extra SDK), reuse CodexRouter.psm1, Hide-AuthEmail, and never Start-Process ChatGPT.exe without the existing .cmd wrapper.

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. 2d ago First seen · 16 lines · 227 tokens per session scan A 2c656ccd0185

Subscribe to this mod's changes

codex-multi-profile AGENTS.md is an instructions file published in the GitHub repository Hung2124/codex-multi-profile (93 stars, last pushed 12d ago), licensed MIT. It adds 227 tokens to every session, about $0.0011 per session on Opus 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.

Testingagent-skillschatgptopenai-codexpowershellwindows
Related

Other instructions, from other repositories

codex-usage-widget AGENTS.md

Instructions for ognjeeen/codex-usage-widget, covering agents.md, project, scope and decision discipline, authorization and repository safety and architecture boundaries.

ognjeeen/codex-usage-widget · 1,218 tokens

local-coding-agent AGENTS.md

AGENTS.md instructions for LongNgn204/local-coding-agent, covering agents.md — setup guide for ai coding agents, what this is, install (one command), run and verify (always do this).

LongNgn204/local-coding-agent · 913 tokens

project-files-readonly-mcp AGENTS.md

AGENTS.md instructions for 13030109506/project-files-readonly-mcp: Read README.md, docs/SECURITYMODEL.md, and docs/WINDOWSTUNNEL.md before changing security or deployment behavior.

13030109506/project-files-readonly-mcp · 290 tokens

ceiling AGENTS.md

Instructions for tsouth89/ceiling, covering repository guidelines, current project state, project structure & modules, build, test, run and coding style & naming.

tsouth89/ceiling · 1,586 tokens

galatea-garden-chatgpt-wake-mcp AGENTS.md

AGENTS.md instructions for mei-shui-xing/galatea-garden-chatgpt-wake-mcp, a project described as: Durable Garden wake inbox and MCP wait tools for ChatGPT Chat on Windows.

mei-shui-xing/galatea-garden-chatgpt-wake-mcp · 384 tokens

Pawse CLAUDE.md

Claude Code instructions for slnu21/Pawse, covering claude.md, what this is, commands, manual gui test — pipe a sample hook json to one event and syntax check without running.

slnu21/Pawse · 2,202 tokens