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.
npx agentmods add instructions/protosskai/chatgpt-context-mcp/agents-mdgit clone --depth 1 https://github.com/protosskai/chatgpt-context-mcpWrote 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/protosskai/chatgpt-context-mcp/agents-md)<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="Measured on agentmods" 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 | $0.00754 | $0.00754 |
| Opus 5 | $0.00377 | $0.00377 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade B, and why
chatgpt-context-mcp AGENTS.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 700 "$HOME/.config/chatgpt-context-mcp" 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:
- Existing process environment variables.
- 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"
}
}
}
}
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.
- 4d ago First seen · 123 lines · 754 tokens per session scan B 7edf2af1d35c
chatgpt-context-mcp AGENTS.md is an instructions file published in the GitHub repository protosskai/chatgpt-context-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 754 tokens to every session, about $0.0038 per session on Opus 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.
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.