What is Chat2Agent AGENTS.md?

A project instruction file for Chat2Agent, an open-source bridge that lets ChatGPT's web conversations reach a local computer through an MCP and OAuth connection. MCP is a standard way for AI systems to call external tools.

Use it when developing or reviewing the bridge, its local-workspace access, resource discovery, provider integrations, or web-facing capability rules.

It defines safety and product boundaries so the bridge can expose selected local capabilities without changing the local coding agent or leaking private resources.

Chat2Agent AGENTS.md — Instructions file by xiaoxiao341

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/xiaoxiao341/chat2agent/agents-md

Clone the repo

git clone --depth 1 https://github.com/xiaoxiao341/Chat2Agent

Made for: Codex, OpenCode.

Per session 275 This file is loaded in full into every session.

When invoked 275 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.

Model	Per session	Once invoked
Fable 5	$0.00275	$0.00275
Opus 5	$0.00138	$0.00138
Sonnet 5	$0.00055	$0.00055
Haiku 4.5	$0.00028	$0.00028

Measured 2d ago against content hash 059faf8a0444, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Chat2Agent 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 · 10 lines

What it actually says

Project Scope

This repository exists to let ChatGPT's web conversation mode reach the local machine through a public MCP/OAuth bridge and perform coding work as close as practical to a Codex Agent.
Do not modify or disrupt the local Codex Agent, including its installed capabilities, global configuration, or normal local workflow.
The local Codex Agent is not a product client or part of the runtime topology. However, DevSpace may discover and expose selected reusable Codex resources, such as applicable AGENTS.md instructions, Skills, and compatible Hook behavior, to ChatGPT web conversations without changing the originals or the local Codex runtime.
Reuse Codex resources through read-only discovery or an explicit compatibility layer. Keep unsupported, secret-bearing, machine-private, or local-runtime-only resources out of the web-facing capability surface.
Provider-backed Subagents are optional integrations, not part of the default web-chat capability path. They may consume the selected local provider account or API quota and must never be recommended or launched implicitly.
Product recommendations and implementation should focus on the web ChatGPT connector experience, remote coding capability, reliability, observability, and security.
Full C:\ and D:\ access is an explicit requirement for the owner's deployment. Open-source defaults and examples may use narrower roots, but must not redefine the owner's deployment requirement.

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.

2d ago First seen · 10 lines · 275 tokens per session scan A 059faf8a0444

Subscribe to this mod's changes

Chat2Agent AGENTS.md is an instructions file published in the GitHub repository xiaoxiao341/Chat2Agent (5 stars, last pushed 9d ago), licensed MIT. It adds 275 tokens to every session, about $0.0014 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.

Building agents

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 · 6,785 tokens

Chat2Agent AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Project Scope

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

spec-kit AGENTS.md

codex AGENTS.md

langchain AGENTS.md

vscode oss-third-party-notices.instructions.md

next.js AGENTS.md