Borrowing it
Nothing to install: this file belongs to Hung2124/codex-multi-profile. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Hung2124/codex-multi-profile/main/AGENTS.mdgit clone --depth 1 https://github.com/Hung2124/codex-multi-profileWrote 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.
[](https://agentmods.dev/instructions/hung2124/codex-multi-profile/agents-md)<a href="https://agentmods.dev/instructions/hung2124/codex-multi-profile/agents-md"><img src="https://agentmods.dev/badge/instructions/hung2124/codex-multi-profile/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.
<a href="https://agentmods.dev/instructions/hung2124/codex-multi-profile/agents-md"><img src="https://agentmods.dev/badge/instructions/hung2124/codex-multi-profile/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00343 | $0.00343 |
| Opus 5.5 | $0.00137 | $0.00137 |
| Sonnet 5.5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00034 | $0.00034 |
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 1mo 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.
What it actually says
AGENTS.md
Windows-only helper: several ChatGPT logins for the Microsoft Store Codex, switched from the Codex avatar menu.
- Read
SKILL.mdanddocs/architecture.mdbefore changing launch or switch behavior. - Start the Store Codex only through
Start-CodexStore(IApplicationActivationManager). Do not copy / cloneChatGPT.exe(26.9xx needs package identity), do not useInvoke-CommandInDesktopPackageorshell:AppsFolder(both hang from a normal process), do not patch Codex files. - Keep the helper cheap: no
Runtime.enable(console flood), no JSON parsing of CDP replies, no WMI in the loop.Page.enablestays: without it the injected script is not re-added after Codex reloads its window. - Page input goes through
ConvertFrom-CodexSwitcherMessage. Only masked emails reach the page. The injected script builds DOM withcreateElementonly (tests enforce this). - Never drop a login that is not saved (
Clear-CodexLiveAuthrefuses). Sync the liveauth.jsoninto its account before replacing it. .ps1/.psm1files stay ASCII (Windows PowerShell 5.1 reads BOM-less UTF-8 as ANSI). Remember thatConvertFrom-Jsonon 5.1 emits a JSON array as one object in a pipeline: assign it first.- Never commit
auth.json, theaccountsfolder or logs. Runtests/Run-All.ps1after edits.
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.
- 1mo ago Changed · +2 lines · +116 tokens per session fe0b19cfa462
- 2mo ago First seen · 16 lines · 227 tokens per session scan A 2c656ccd0185
codex-multi-profile AGENTS.md is an instructions file published in the GitHub repository Hung2124/codex-multi-profile (94 stars, last pushed 9d ago), licensed MIT. It adds 343 tokens to every session, about $0.0014 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.
codex-multi-profile AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codex-multi-profile AGENTS.mdHung2124/codex-multi-profile | Instructions file | 94 | 9d ago | MIT | A | 343 | 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 | 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 |