agentmods.dev

codex-third-party-subagents AGENTS.md

codex-third-party-subagents AGENTS.md is an instructions file for Codex, OpenCode from dhy365-creator/codex-third-party-subagents. It costs 518 tokens per session, scanned A, original, MIT.

A repository guide for Codex Third-Party Subagents, an unofficial macOS tool for routing requests between AI providers. It defines the project's scope and rules for agents working on it.

In plain words
What is it for?
It helps agents make changes, validate code, handle routing rules, and work within the repository's Node.js and macOS constraints.
Why use it?
It gives coding agents the project context and safety limits they need, such as protecting secrets, keeping dry-run as the default, and not running provider setup scripts.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: reads ~/.codex or $CODEX_HOME, but also the file is AGENTS.md. Also seen: mentions subagents; mentions AGENTS.md; mentions Codex.

not rated 11 4d ago A scan 518 tokens original MIT
View the source file dhy365-creator/codex-third-party-subagents
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/dhy365-creator/codex-third-party-subagents/agents-md
Clone the repo
git clone --depth 1 https://github.com/dhy365-creator/codex-third-party-subagents

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for codex-third-party-subagents AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dhy365-creator/codex-third-party-subagents/agents-md.svg)](https://agentmods.dev/instructions/dhy365-creator/codex-third-party-subagents/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dhy365-creator/codex-third-party-subagents/agents-md"><img src="https://agentmods.dev/badge/instructions/dhy365-creator/codex-third-party-subagents/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 518 This file is loaded in full into every session.
When invoked 518 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 5.1 $0.00518 $0.00518
Opus 5 $0.00259 $0.00259
Sonnet 5 $0.00104 $0.00104
Haiku 4.5 $0.00052 $0.00052

Measured 6d ago against content hash d4644e2d5c6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

codex-third-party-subagents 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 6d 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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project scope

  • Unofficial, macOS-only public beta for Codex Third-Party Subagents (codex-third-party-subagents): a provider-pack-based Codex Desktop fallback routing stack.
  • Text, code, research synthesis, and local validation only. No image, audio, video, desktop, or browser handling. DeepSeek V4 Pro is explicit-only: never auto-route to it or broaden its controlled maintainer runtime evidence into a public-installer, independent-user, or general support claim.
  • Node.js >=20, standard library only. No third-party runtime dependencies.

Rules for agents working here

  • Do not hardcode, commit, or log secrets. API keys live in the macOS Keychain and are read at runtime only.
  • Do not execute any official provider setup script. Catalog data is retrieved at install time as inert text (documented, never executed) with a local catalog-source override; do not vendor official catalog or prompt files.
  • CLI changes must keep dry-run as the default; writes require an explicit --apply.
  • Custom Agent identity comes from the official TOML name field in ~/.codex/agents; routing policy must not be documented as Host registration.
  • The task bridge allows exactly one active provider task. Active slot and task file are owner-only (0700 / 0600), reject symlinks, and are atomically archived to completed-* or failed-*. Never overwrite or delete archives.
  • Desktop preflight is a policy-assisted guardrail, not guaranteed native automatic interception. Document it as defense-in-depth.
  • Preserve unrelated local changes. Make minimal, scoped diffs.
  • Keep files small: JS/TS under 300 lines, docs concise.
  • Update docs/current-state.md and docs/tasks.md on durable changes. Documented capabilities must match the implementation.
  • GitHub Actions workflows must use read-only permissions and no secrets.

Layout

  • src/, scripts/, tests/ — implementation and generated-file templates.
  • docs/ — architecture, configuration (中文), troubleshooting, state, tasks.
  • .github/workflows/test.yml — read-only test workflow.

Read the full file on GitHub · 46 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. 6d ago First seen · 46 lines · 518 tokens per session scan A d4644e2d5c6b

Subscribe to this mod's changes

codex-third-party-subagents AGENTS.md is an instructions file published in the GitHub repository dhy365-creator/codex-third-party-subagents (11 stars, last pushed 4d ago), licensed MIT. It adds 518 tokens to every session, about $0.0026 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.

codexcodex-desktopdeepseekmacossubagentsthird-party-models
Related

Other instructions, from other repositories

codex-provider-sync AGENTS.md

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

DeepSeek-Harness-Desktop AGENTS.md

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

dev-flow AGENTS.md

AGENTS.md instructions for Innocent-children/dev-flow, covering dev flow repository instructions, authority, requirement scope, architecture and current design and product feature proposals.

Innocent-children/dev-flow · 3,070 tokens

DeepSeekMeter AGENTS.md

Instructions for CWNU-Open-Source-Community/DeepSeekMeter, covering agents.md — deepseekmeter 仓库操作规范, 1. 项目是什么, 2. 常用命令（改动后必须本地验证）, ios 版验证（核心包自测 + 工程结构静态校验必跑；有 xcode 时还会构建 app 冒烟） and android 核心单测（需 jdk 17 + android sdk；jvm 直跑无需设备）.

CWNU-Open-Source-Community/DeepSeekMeter · 3,490 tokens

claude-science-api-bridge AGENTS.md

Instructions for Jyx0208/claude-science-api-bridge, covering agent operating manual, prime directive, goal, repository map and success criteria.

Jyx0208/claude-science-api-bridge · 1,090 tokens

ClawRouter CLAUDE.md

Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.

BlockRunAI/ClawRouter · 686 tokens