Codex-Manager is a local account management and switching tool for the Codex command-line interface, with a local gateway that forwards requests. It is for users who need to manage multiple Codex CLI accounts and choose between them.
Borrowing it
Nothing to install: this file belongs to qxcnm/Codex-Manager. 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/qxcnm/Codex-Manager/main/AGENTS.mdgit clone --depth 1 https://github.com/qxcnm/Codex-ManagerWrote 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/qxcnm/codex-manager/agents-md)<a href="https://agentmods.dev/instructions/qxcnm/codex-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/qxcnm/codex-manager/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/qxcnm/codex-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/qxcnm/codex-manager/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 | $0.01221 | $0.01221 |
| Opus 5.5 | $0.00488 | $0.00488 |
| Sonnet 5.5 | $0.00244 | $0.00244 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
Codex-Manager 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Engineering Standards
This file applies to the whole CodexManager repository. For work under apps/,
also read apps/AGENTS.md; that file contains the more specific frontend and
Tauri rules.
1. Project Shape
apps/: Next.js frontend plus the Tauri desktop shell.apps/src/: App Router UI, components, hooks, API clients, runtime helpers, i18n, and Zustand state.apps/src-tauri/: Tauri v2 application shell, desktop lifecycle, tray/window behavior, native commands, and desktop RPC client code.crates/core/: SQLite migrations, storage primitives, auth helpers, and core usage/account data structures.crates/service/: local HTTP/RPC service, gateway routing, protocol adapters, account/API key/usage domains, plugins, app settings, and runtime sync.crates/web/: service-mode Web UI shell, embedded static UI serving, and/api/runtime//api/rpcproxy behavior.crates/start/: service-mode launcher that starts service + web together.scripts/,docker/,.github/: build, release, probe, container, and CI automation.
2. Ownership Boundaries
- Keep UI behavior in
apps/src/, desktop shell behavior inapps/src-tauri/, and service/gateway behavior incrates/service/. - Put schema and persistence foundation changes in
crates/core/, especially SQLite migrations and reusable storage helpers. - Avoid expanding central entrypoints with unrelated orchestration. Large files should be treated as legacy surfaces; new substantial logic should move into focused modules, hooks, or domain helpers.
- Do not mix release/script changes with product behavior unless the task explicitly requires it.
3. API, RPC, and Command Sync
- Frontend code must call backend capabilities through typed wrappers in
apps/src/lib/api/. - Desktop IPC should use the centralized
invoke/invokeFirsthelpers from@/lib/api/transport; do not use rawfetch()for desktop commands. - Service commands that require a service address should pass parameters through
withAddr(). App-shell commands such asapp_*,open_*, and window/update helpers may omit it when no service address is needed. - Web/service-mode fallback is allowed only through the existing transport
stack:
transport.ts,transport-web-commands.ts,rpc-http.ts, andfetchWithRetry. - When adding or renaming a backend command, keep the chain synchronized: Rust implementation, Tauri command registry when applicable, service RPC dispatch/Web command mapping when applicable, and the frontend API wrapper.
- Preserve the existing underscore command names and camelCase RPC method mapping conventions.
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 First seen · 99 lines · 1,221 tokens per session scan A a6ec1faeae6c
Codex-Manager AGENTS.md is an instructions file published in the GitHub repository qxcnm/Codex-Manager (3,014 stars, last pushed 6d ago), licensed MIT. It adds 1,221 tokens to every session, about $0.0049 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.