chatgpt-context-mcp: Instructions file for Codex

AGENTS.md

chatgpt-context-mcp AGENTS.md is an instructions file for Codex, OpenCode from protosskai/chatgpt-context-mcp. It costs 754 tokens per session, scanned B, original, MIT.

A repository instruction file describing how coding agents should work on the chatgpt-context-mcp project, including commands, setup, and limits on supported features.

In plain words
What is it for?
Use it when working on this project to find its supported ChatGPT conversation URLs, local MCP setup, build commands, tests, and type checks.
Why use it?
It gives agents the project context and required checks they need before making or finishing changes.

Instructions file for CodexOpenCode

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

This is protosskai/chatgpt-context-mcp's own configuration. It tells Codex and OpenCode how to work on chatgpt-context-mcp 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 chatgpt-context-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to protosskai/chatgpt-context-mcp. 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/protosskai/chatgpt-context-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/protosskai/chatgpt-context-mcp

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 chatgpt-context-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/protosskai/chatgpt-context-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/protosskai/chatgpt-context-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/protosskai/chatgpt-context-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/protosskai/chatgpt-context-mcp/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 chatgpt-context-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/protosskai/chatgpt-context-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/protosskai/chatgpt-context-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 754 This file is loaded in full into every session.
When invoked 754 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00754 $0.00754
Opus 5.5 $0.00302 $0.00302
Sonnet 5.5 $0.00151 $0.00151
Haiku 4.5 $0.00075 $0.00075

Measured 2mo ago against content hash 7edf2af1d35c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

chatgpt-context-mcp AGENTS.md scanned grade B with 1 finding 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 2mo 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 700 "$HOME/.config/chatgpt-context-mcp"
AGENTS.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide

This file is for Codex, Claude Code, and other coding agents working in this repository.

Project Summary

chatgpt-context-mcp is a local stdio MCP server that imports private ChatGPT conversation context into MCP clients.

Supported URLs:

https://chatgpt.com/c/{conversation_id}
https://chat.openai.com/c/{conversation_id}

Do not add support for shared links, ChatGPT Projects, bulk export, attachment downloads, or browser automation unless the user explicitly asks for a new design and approves it.

Required Commands

Before finishing changes, run:

npm test
npm run typecheck
npm run build

For release-readiness checks, run:

npm run check

Local MCP Setup

Build first:

npm install
npm run build

The built server entrypoint is:

<repo-path>/dist/src/server.js

The recommended startup command for desktop MCP clients is:

<repo-path>/scripts/start-mcp.sh

The wrapper uses this precedence:

  1. Existing process environment variables.
  2. Fallback values from $HOME/.config/chatgpt-context-mcp/env.

Create the fallback file:

mkdir -p "$HOME/.config/chatgpt-context-mcp"
chmod 700 "$HOME/.config/chatgpt-context-mcp"
cat > "$HOME/.config/chatgpt-context-mcp/env" <<'EOF'
export CHATGPT_BEARER_TOKEN="<chatgpt-bearer-token>"
export CHATGPT_ACCOUNT_ID=""
EOF
chmod 600 "$HOME/.config/chatgpt-context-mcp/env"

Do not commit token files or real bearer tokens.

Codex Config Example

[mcp_servers.chatgpt_context]
command = "<repo-path>/scripts/start-mcp.sh"
args = []
env_vars = ["CHATGPT_BEARER_TOKEN", "CHATGPT_ACCOUNT_ID", "CHATGPT_CODEX_MCP_CACHE_DIR", "CHATGPT_CODEX_MCP_ENV_FILE"]
startup_timeout_sec = 10
tool_timeout_sec = 120
default_tools_approval_mode = "auto"

Claude Code Config Example

{
  "mcpServers": {
    "chatgpt_context": {
      "command": "<repo-path>/scripts/start-mcp.sh",
      "args": [],
      "env": {
        "CHATGPT_CODEX_MCP_ENV_FILE": "$HOME/.config/chatgpt-context-mcp/env"
      }
    }
  }
}

Read the full file on GitHub · 123 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. 2mo ago First seen · 123 lines · 754 tokens per session scan B 7edf2af1d35c

Subscribe to this mod's changes

chatgpt-context-mcp AGENTS.md is an instructions file published in the GitHub repository protosskai/chatgpt-context-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 754 tokens to every session, about $0.0030 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

chatgpt-context-mcp AGENTS.md compared with instructions from other repositories

chatgpt-context-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
chatgpt-context-mcp AGENTS.mdprotosskai/chatgpt-context-mcpInstructions file14mo agoMITB754Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot