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 instructions/ndycode/codex-multi-auth/agents-mdgit 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 | $0.02766 | $0.02766 |
| Opus 5 | $0.01383 | $0.01383 |
| Sonnet 5 | $0.00553 | $0.00553 |
| Haiku 4.5 | $0.00277 | $0.00277 |
Grade B, and why
codex-multi-auth AGENTS.md scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Official Codex state: `~/.codex/auth.json`, `~/.codex/accounts.json`, `~/.codex/config.toml`. How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PROJECT KNOWLEDGE BASE
Generated: 2026-04-25 Commit: 6147f88 Validated: 2026-06-10 against commit 98d9819 (repo audit; claims re-checked against the tree, content not regenerated) Branch: main Package version: 2.9.2
OVERVIEW
codex-multi-auth is a Codex CLI-first OAuth account manager and optional forwarding wrapper for the official Codex CLI. The installed codex-multi-auth entrypoint handles account-management commands locally, codex-multi-auth-codex forwards official Codex commands through this package's wrapper when explicitly used, mcodex is a convenience launcher over that wrapper, and runtime rotation can route live Responses traffic through a localhost account-rotation proxy by default. Local governance modules (usage ledger, budgets, account policies, routing profiles, local bridge) stay file-backed under the multi-auth root. The plugin-host entrypoint remains exported for compatibility, but the primary product surface is the account manager, optional wrapper, storage, runtime proxy, governance commands, and repair tooling.
STRUCTURE
./
├── scripts/
│ ├── codex.js # codex-multi-auth-codex wrapper, official CLI forwarder, shadow CODEX_HOME/runtime proxy setup
│ ├── codex-multi-auth.js # standalone package CLI entrypoint
│ ├── mcodex.js # convenience launcher: forwards to codex.js; optional --monitor / --tmux
│ ├── codex-routing.js # auth command and compatibility alias routing
│ ├── codex-bin-resolver.js # official Codex binary discovery
│ ├── codex-app-router.js # persistent localhost router for packaged Codex app bind
│ └── codex-app-launcher.js # reversible user-level app launcher routing helper
├── index.ts # optional plugin-host runtime entry
├── lib/ # core runtime logic (see lib/AGENTS.md)
│ ├── auth/ # OAuth flow, PKCE, callback server
│ ├── runtime/ # Codex CLI/app integration helpers, app bind, first-run, live sync, runtime observability
│ ├── request/ # request transform, SSE, failover, backoff
│ ├── storage/ # path resolution, migrations, backups, restore, import/export
│ ├── policy/ # runtime policy composition (budgets, tags, routing profiles)
│ ├── usage/ # local usage ledger, pricing, redaction
│ ├── codex-cli/ # Codex CLI state sync and writer helpers
│ ├── codex-manager/ # command modules and settings panels
│ ├── prompts/ # model-family prompts, GitHub ETag cache
│ ├── recovery/ # conversation recovery state
│ ├── tools/ # hashline helper tools
│ └── ui/ # TUI rendering, menus, copy, theme, select
├── test/ # vitest suites (see test/AGENTS.md)
├── docs/ # user, reference, release, audit, and maintainer docs
├── config/ # optional plugin-host config templates
├── vendor/ # vendored codex-ai-plugin + codex-ai-sdk shims
├── assets/ # static assets
├── .github/ # CI, issue/PR templates, plugin scanner fixtures
└── dist/ # build output (generated, do not edit)
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.
- 2d ago First seen · 145 lines · 2,766 tokens per session scan B da8a0f94622a
codex-multi-auth AGENTS.md is an instructions file published in the GitHub repository ndycode/codex-multi-auth (465 stars, last pushed 2d ago), licensed MIT. It adds 2,766 tokens to every session, about $0.0138 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codexia AGENTS.md
Instructions for milisp/codexia, covering agents.md, project info, project tech, common commands and project structure.
codexU AGENTS.md
Instructions for shanggqm/codexU, covering agents.md, 项目边界, 关键文档, 代码结构 and 项目级 skills.
oauth2-mock-server AGENTS.md
Instructions for axa-group/oauth2-mock-server, covering agent guidelines, project overview, module map, mandatory checks before finishing any task and 1. lint.
oauth2-mock-server copilot-instructions.md
Instructions for axa-group/oauth2-mock-server: This repository contains oauth2-mock-server, a TypeScript library and CLI tool providing a configurable OAuth2/OpenID Connect mock server for automated testing.
rembric CLAUDE.md
Instructions for susomejias/rembric, covering claude.md, quick reference, claims need evidence, architecture and data access pattern.
local-agent-viewer CLAUDE.md
Instructions for maxturazzini/local-agent-viewer, covering claude.md, what this is, commands, parse & serve and unified cli — query & kb management (zero extra deps).