agentmods.dev

codex-switch AGENTS.md

A set of repository instructions for codex-switch that keeps Windows and macOS implementation work separate where possible.

In plain words
What is it for?
It is for deciding where Windows and macOS code belongs and choosing the matching build, check, test, and compilation commands.
Why use it?
It prevents platform-specific changes from being mixed unnecessarily and avoids running checks for an unrelated operating system.

Instructions file for CodexOpenCode

1 2mo ago A scan 227 tokens original MIT
View the source file ChArLiEdance/codex-switch
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/charliedance/codex-switch/agents-md
Clone the repo
git clone --depth 1 https://github.com/ChArLiEdance/codex-switch

Made for: Codex, OpenCode.

Per session 227 This file is loaded in full into every session.
When invoked 227 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 $0.00227 $0.00227
Opus 5 $0.00113 $0.00113
Sonnet 5 $0.00045 $0.00045
Haiku 4.5 $0.00023 $0.00023

Measured 2d ago against content hash bc57701bfc1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-switch 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 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.

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 · 11 lines

What it actually says

Repository AGENTS

Platform Isolation

  • Windows and macOS should be developed independently whenever practical.
  • Do not introduce shared modules or shared runtime paths unless the behavior is a necessary cross-platform contract, disk format, or build/versioning concern.
  • Do not extract or expand shared modules for platform-specific behavior unless the shared code is strictly necessary for identical cross-platform contracts, on-disk formats, or version/build plumbing.
  • When syncing a feature from one platform to the other, prefer implementing or adapting it under src-tauri/win/** or src-tauri/mac/** first. Use src-tauri/shared/** only for unavoidable neutral contracts.
  • For Windows-only changes, use Windows-only compile, check, test, and build commands; do not run validation paths that require compiling src-tauri/mac/** unless the task explicitly touches macOS.
  • Windows Vite/Tauri build commands should be run with escalation by default. In this repository, sandboxed builds are known to fail with spawn EPERM while starting esbuild from the Vite/Tauri beforeBuildCommand.
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. 2d ago First seen · 11 lines · 227 tokens per session scan A bc57701bfc1b

Subscribe to this mod's changes

codex-switch AGENTS.md is an instructions file published in the GitHub repository ChArLiEdance/codex-switch (1 stars, last pushed 2mo ago), licensed MIT. It adds 227 tokens to every session, about $0.0011 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.

account-switchercodex-clidesktop-appmacosopenai-codex
Related

Other instructions, from other repositories

codex-token-meter AGENTS.md

Instructions for prefect12/codex-token-meter, covering ai token meter development guide, project shape, build and verification, git workflow and ai token meter test loop.

prefect12/codex-token-meter · 1,357 tokens

codex-provider-sync AGENTS.md

Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.

Dailin521/codex-provider-sync · 1,480 tokens

ai-code-interface.el AGENTS.md

Instructions for tninja/ai-code-interface.el, covering agents.md, common development commands, byte compilation, running tests and run a specific test file.

tninja/ai-code-interface.el · 2,539 tokens

ai-code-interface.el copilot-instructions.md

Instructions for tninja/ai-code-interface.el, covering github copilot instructions for ai-code-interface.el, project overview, language and technology, code style and conventions and file naming.

tninja/ai-code-interface.el · 1,289 tokens

DeepSeek-Harness-Desktop AGENTS.md

Instructions for web-casa/DeepSeek-Harness-Desktop, covering agents.md — dsh desktop, 项目本质, 不可违背的安全不变量, 版本单一事实源（改动版本时必须同时改全部） and harness 升级启动契约（bump pin 前必读）.

web-casa/DeepSeek-Harness-Desktop · 2,781 tokens

codex-trace AGENTS.md

Instructions for PixelPaw-Labs/codex-trace, covering claude.md, commands, dev, lint and format.

PixelPaw-Labs/codex-trace · 611 tokens