codex-auth-switcher AGENTS.md

A repository instruction guide for agents working on codex-switch, a Go command-line tool that manages local Codex authentication profiles.

In plain words
What is it for?
It is for guiding development of authentication-profile storage, switching and rollback, usage capture, filesystem permissions, and safe command output.
Why use it?
It gives coding agents the project’s structure, security limits, required documents, and correctness rules before they make changes.

Instructions file for CodexOpenCode

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/curserio/codex-auth-switcher/agents-md
Clone the repo
git clone --depth 1 https://github.com/curserio/codex-auth-switcher

Made for: Codex, OpenCode.

Per session 1,559 This file is loaded in full into every session.
When invoked 1,559 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 $0.01559 $0.01559
Opus 5 $0.00779 $0.00779
Sonnet 5 $0.00312 $0.00312
Haiku 4.5 $0.00156 $0.00156

Measured yesterday against content hash f4b421607ee0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-auth-switcher 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 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.

AGENTS.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository development guide

Purpose

This file contains repository-specific rules for humans and automated coding agents.

Follow the global engineering guide for general planning, Git safety, scope control, test-first development, verification, and reporting.

Also read:

  • README.md
  • SECURITY.md
  • Makefile
  • go.mod
  • .github/workflows/ci.yml

Do not add model routing, personal settings, or other machine-specific configuration to this repository guide.

Project map

codex-switch is an unofficial Go CLI for managing local OpenAI Codex CLI authentication profiles.

  • cmd/codex-switch/ — CLI entry point.
  • internal/app/ — command dispatch, orchestration, and user-visible output.
  • internal/auth/ — extraction of non-secret account identity metadata.
  • internal/store/ — profile storage, atomic writes, switching, rollback, cleanup, and filesystem permissions.
  • internal/usage/ — live codex app-server usage capture and normalization.
  • .github/workflows/ci.yml — authoritative CI validation sequence.

Correctness, rollback behavior, filesystem permissions, and secret-safe output take priority over convenience.

Security boundaries

Read SECURITY.md before changing authentication, profile storage, switching, cleanup, permissions, or account-related output.

Never print, commit, attach, or retain as evidence:

  • auth.json or its raw contents;
  • JWTs or OAuth tokens;
  • access, refresh, or bearer tokens;
  • contents of ~/.codex-auth-switcher;
  • Codex session logs;
  • unredacted account identifiers;
  • terminal output or screenshots containing authentication data.

Tests and routine validation must never read or mutate the developer's real Codex state.

Do not run these commands against the default user environment as routine validation:

  • codex-switch add;
  • codex-switch use;
  • codex-switch rename;
  • codex-switch delete;
  • codex-switch capture;
  • codex-switch prepare-login;
  • codex-switch cleanup --apply;
  • equivalent mutating commands through go run;
  • make install;
  • Codex login or logout flows.

Read the full file on GitHub · 206 lines

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. yesterday First seen · 206 lines · 1,559 tokens per session scan A f4b421607ee0

Subscribe to this mod's changes

codex-auth-switcher AGENTS.md is an instructions file published in the GitHub repository curserio/codex-auth-switcher (1 stars, last pushed 27d ago), licensed MIT. It adds 1,559 tokens to every session, about $0.0078 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 2026-08-31.