CodexHost is a desktop application that lets users run coding-agent harnesses such as Pi and Claude Code inside Codex Desktop. It is for people who want to choose among multiple agents and have them delegate tasks to one another while staying in one workspace.
Borrowing it
Nothing to install: this file belongs to BytePioneer-AI/codex-host. 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/BytePioneer-AI/codex-host/main/AGENTS.mdgit clone --depth 1 https://github.com/BytePioneer-AI/codex-hostWrote 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/bytepioneer-ai/codex-host/agents-md)<a href="https://agentmods.dev/instructions/bytepioneer-ai/codex-host/agents-md"><img src="https://agentmods.dev/badge/instructions/bytepioneer-ai/codex-host/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/bytepioneer-ai/codex-host/agents-md"><img src="https://agentmods.dev/badge/instructions/bytepioneer-ai/codex-host/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 | $0.01080 | $0.01080 |
| Opus 5 | $0.00540 | $0.00540 |
| Sonnet 5 | $0.00216 | $0.00216 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
codex-host 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Product Intent
codexhost runs external Agent Harnesses as independent Threads inside Codex Desktop, preserving the official shell and native Codex path. Integrate each Harness through its native interface; preserve its actual capabilities and semantics rather than inventing equivalent-looking Host behavior.
Code Layout
Native Rust
crates/launcher/: native application launchshim/: process proxyingupdater/: update installationplatform/: cross-platform native integration
TypeScript Workspace
packages/protocol-core/: Host protocol routing and projectionmapping-store/: external Thread metadata persistenceharness-adapter/: public Harness session and plugin contractsharness-discovery/: Harness executable discovery and invocation helpersharness-broker/: native Broker communication; currently retains Claude Code-specific semanticsadapters/: Harness-specific implementations and plugin entry pointsdesktop-control/: CDP / Electron Inspector-driven Desktop interactionhost-runtime/: Host composition and installed plugin loadingupdate-manager/: background update preparationshared-contracts/: browser-safe types and runtime schemasrenderer-extension/: browser JavaScript extension
Build and Release
scripts/release/: release preparation, packaging, and publishingtools/: development utilities and technical Gates
Boundary Rules
- Rust owns native launch, process management, update installation, and platform integration. It must not own Host protocol or Harness semantics.
shared-contractsmust remain browser-safe and independent of other Workspace packages.renderer-extensionmust not import Node.js built-ins, Electron private APIs, or Harness SDKs.- Harness-specific protocol details must remain inside the corresponding Adapter.
- Host Runtime loads installed plugins through public contracts, not direct imports of concrete Adapter packages. The preinstalled set belongs to
scripts/release/harness-plugins.json, not Host registration code. - Use package public exports for cross-package dependencies. Read
tools/check-boundaries.mjsbefore changing dependency directions; it is the executable boundary check run bynpm run lint.
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 Changed · +6 lines · +251 tokens per session 47ac5f94a6d6
- 9d ago First seen · 73 lines · 829 tokens per session scan A eb96a395e41f
codex-host AGENTS.md is an instructions file published in the GitHub repository BytePioneer-AI/codex-host (2,026 stars, last pushed today), licensed MIT. It adds 1,080 tokens to every session, about $0.0054 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.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.