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.
npx agentmods add skills/ndycode/codex-multi-auth/codex-auth-setupnpx skills add ndycode/codex-multi-auth --skill codex-auth-setupgit clone --depth 1 https://github.com/ndycode/codex-multi-authWhat 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 | $0.00032 | $0.00495 |
| Opus 5 | $0.00016 | $0.00247 |
| Sonnet 5 | $0.00006 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
codex-auth-setup 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 yesterday.
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
codex-auth-setup
Use this skill when the user wants to install, reinstall, upgrade, or troubleshoot codex-multi-auth for the official @openai/codex CLI.
Install
npm i -g @openai/codex
npm i -g codex-multi-auth
If the old scoped prerelease package is still installed:
npm uninstall -g @ndycode/codex-multi-auth
npm i -g codex-multi-auth
First login
codex-multi-auth login
Default flow:
- Open the account menu.
- Choose the browser-first OAuth path.
- Complete the official OAuth flow.
- Return to the terminal and confirm the account was saved.
Verify health and routing
codex-multi-auth status
codex-multi-auth list
codex-multi-auth check
codex-multi-auth forecast --live
Use these next when managing multiple accounts:
codex-multi-auth switch 2
codex-multi-auth verify-flagged
codex-multi-auth doctor --fix
Alternate login paths
Use these when browser launch is blocked or the shell is headless:
codex-multi-auth login --manual
CODEX_AUTH_NO_BROWSER=1 codex-multi-auth login
Troubleshooting
- Run
where codex-multi-authifcodex-multi-authis not recognized. - Free port
1455and retry if the OAuth callback server cannot bind. - Re-run
codex-multi-auth loginif the active account is stale or the wrong account was selected. - Use
codex-multi-auth doctor --fixfollowed bycodex-multi-auth checkfor a fast recovery loop. - See
docs/getting-started.md,docs/configuration.md,docs/troubleshooting.md, anddocs/reference/commands.mdfor the full command and config docs.
Usage boundaries
This project is for personal development use. For production or commercial workloads, use the OpenAI Platform API.
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.
- yesterday First seen · 74 lines · 32 tokens per session scan A 2ee4bed8542a
codex-auth-setup is a skill published in the GitHub repository ndycode/codex-multi-auth (465 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 495 once invoked, about $0.0002 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.
Other skills, from other repositories
codex-auth
🧩 Codex Skill — Refresh Codex CLI auth.json from ChatGPT. Skipphone verification, no overseas number needed. For users behind firewalls, in WSL, or remote desktop.
mcp-oauth-remote-gateway
Manual OAuth for remote MCP servers on headless gateways.
pretext
Build creative browser demos with DOM-free text layout.
save-as-pdf
Reformat the current HTML design into a paginated, paper-ready PDF. The "Instant" export already gives the user a PDF at the design's native pixel size — this path is for when they want real pages.
9router-web-fetch
Fetch URL → markdown / text / HTML via 9Router /v1/web/fetch using Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.
claude-in-chrome
Automates your Chrome browser to interact with web pages - clicking elements, filling forms, capturing screenshots, reading console logs, and navigating sites. Opens pages in new tabs within your existing Chrome session. Requires site-level permissions before executing (configured in the extension).