Local-Codex-Bridge: Instructions file for Codex

AGENTS.md

Local-Codex-Bridge AGENTS.md is an instructions file for Codex, OpenCode from zoeynine/Local-Codex-Bridge. It costs 3,588 tokens per session, scanned A, original, MIT.

Project guidance for Local Codex Bridge, a small bridge that lets an AI client supervise official Codex sessions through a standard tool connection. It describes the components, security boundaries, and the limited state the bridge should keep.

In plain words
What is it for?
Working on the tool connection, Codex process communication, public tools, live session state, checkpoints, and optional Windows, macOS, or secure tunnel features.
Why use it?
It helps contributors preserve the intended design and avoid turning the bridge into a second task manager, transcript store, or authority system.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex; mentions Cursor.

This is zoeynine/Local-Codex-Bridge's own configuration. It tells Codex and OpenCode how to work on Local-Codex-Bridge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Local-Codex-Bridge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zoeynine/Local-Codex-Bridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zoeynine/Local-Codex-Bridge/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/zoeynine/Local-Codex-Bridge

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 Local-Codex-Bridge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zoeynine/local-codex-bridge/agents-md/github.svg)](https://agentmods.dev/instructions/zoeynine/local-codex-bridge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zoeynine/local-codex-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/zoeynine/local-codex-bridge/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.

agentmods 80×15 button for Local-Codex-Bridge AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zoeynine/local-codex-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/zoeynine/local-codex-bridge/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,588 This file is loaded in full into every session.
When invoked 3,588 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.03588 $0.03588
Opus 5.5 $0.01435 $0.01435
Sonnet 5.5 $0.00718 $0.00718
Haiku 4.5 $0.00359 $0.00359

Measured 27d ago against content hash c1f46b08d306, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Local-Codex-Bridge 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 27d 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 · 401 lines

How it starts

The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Guidance

Release contract: V2.3.4

This file is guidance for AI agents working on Local Codex Bridge. It is not a product overview and should not be treated as a substitute for the source, tests, or protocol qualification notes.

Read the current repository state before acting. Prefer current source and tests over remembered behavior, old issue context, or assumptions about Codex internals.

Project intent

Local Codex Bridge is a thin MCP stdio supervisory surface for native Codex, with one shared Windows/macOS core and optional platform-specific integration layers.

Its purpose is to let ChatGPT or another MCP client supervise native Codex work without creating a second task system, history store, queue, retry loop, semantic index, model registry, or lifecycle authority.

Keep the Bridge thin.

Native Codex owns persistent threads, turns, execution, history, Goal, Queue, Search, model state, sandbox behavior, and approval behavior. Bridge-owned state is limited to bounded live supervision state, pending requests, terminal snapshots, optional bounded checkpoints, and narrow compatibility / UX projection where explicitly implemented.

Do not solve an upstream capability gap by casually inventing a parallel Bridge subsystem.

Runtime architecture

The core chain is:

MCP client
   -> Local Codex Bridge (MCP JSON-RPC over stdio)
   -> official `codex app-server --listen stdio://` (JSONL stdio)
   -> native Codex threads / turns

Primary ownership in the repository:

  • src/mcp.ts — MCP transport boundary and result framing
  • src/app-server.ts — official Codex app-server child process and protocol requests
  • src/tools.ts — public MCP tool schema and supervisory contract
  • src/runtime.ts — bounded ephemeral live state, pending requests, terminal snapshots
  • src/observe-compact.ts — compact typed supervision projection
  • src/history.ts — lossless History delivery checks
  • src/goal.ts — Native Goal validation / delivery
  • src/queue.ts — Native Queue validation / delivery
  • src/search.ts — Native Search validation / delivery
  • src/checkpoint.ts — optional bounded supervisor checkpoint
  • src/platform.ts — Windows/macOS platform boundary
  • src/version.ts — canonical Bridge version
  • PROTOCOL-ASSUMPTIONS.md — version-sensitive upstream contract and revalidation notes

Read the full file on GitHub · 401 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. 27d ago Changed · +2 lines · +50 tokens per session c1f46b08d306
  2. 28d ago Changed · +332 lines · +2,408 tokens per session 4ea1df1e5c47
  3. 1mo ago First seen · 67 lines · 1,130 tokens per session scan A 234aa78fd8ea

Subscribe to this mod's changes

Local-Codex-Bridge AGENTS.md is an instructions file published in the GitHub repository zoeynine/Local-Codex-Bridge (41 stars, last pushed 9d ago), licensed MIT. It adds 3,588 tokens to every session, about $0.0144 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.

Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,786 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens