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/opentabs-dev/opentabs/agents-mdgit clone --depth 1 https://github.com/opentabs-dev/opentabsWhat 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 | $0.07070 | $0.07070 |
| Opus 5 | $0.03535 | $0.03535 |
| Sonnet 5 | $0.01414 | $0.01414 |
| Haiku 4.5 | $0.00707 | $0.00707 |
Grade B, and why
opentabs AGENTS.md scanned grade B with 2 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 3d 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.
ssh pc "sudo systemctl stop ralph-consolidator" # Stop the consolidator Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**Production code** (`platform/*/src/`): Uses Node.js APIs directly (`node:fs/promises`, `node:child_process`, `node:crypto`, `process.env`, `process.argv`). Copies of this mod
1 near-identical copy found in the catalogue:
- opentabs CLAUDE.md — 88% identical, 66 lines differ
How it starts
The opening of the file, as written. The whole thing — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions for Codex
Project Overview
OpenTabs Platform is a Chrome extension + MCP server with a plugin-based architecture. A plugin SDK allows anyone to create OpenTabs plugins as standalone npm packages. The MCP server discovers plugins at runtime, and the Chrome extension dynamically injects plugin adapters into matching tabs — giving AI agents access to web applications through the user's authenticated browser session.
Architecture
┌─────────────┐ Streamable HTTP ┌─────────────┐ WebSocket ┌──────────────────┐
│ Codex │ ←───────────────→ │ MCP Server │ ←─────────→ │ Chrome Extension │
│ │ /mcp │ (localhost) │ │ (Background) │
└─────────────┘ └──────┬──────┘ └────────┬─────────┘
│ │
┌──────▼──────┐ ┌────────▼─────────┐
│ Plugin │ │ Adapter IIFEs │
│ Discovery │ │ (per plugin, │
│ (npm + local│ │ injected into │
│ paths) │ │ matching tabs) │
└─────────────┘ └────────┬─────────┘
│ Same-origin
┌────────▼─────────┐
│ Web APIs │
│ (user's session) │
└──────────────────┘
MCP Server (platform/mcp-server): Plugin discovery, tool dispatch via WebSocket, browser tools, audit log. See platform/mcp-server/AGENTS.md for details.
Chrome Extension (platform/browser-extension): Adapter injection, tool dispatch relay, React side panel UI. Published to npm as @opentabs-dev/browser-extension and bundled as a CLI dependency so opentabs start can auto-install it. See platform/browser-extension/AGENTS.md for details.
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.
- 3d ago First seen · 463 lines · 7,070 tokens per session scan B b0cac6e4d3ca
opentabs AGENTS.md is an instructions file published in the GitHub repository opentabs-dev/opentabs (926 stars, last pushed 9d ago), licensed MIT. It adds 7,070 tokens to every session, about $0.0353 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
hanzi-browse CLAUDE.md
Claude Code instructions for hanzili/hanzi-browse, covering hanzi browse — architecture guide, what is hanzi browse?, architecture, key directories and value propositions.
neobrowser AGENTS.md
Instructions for pitiflautico/neobrowser, covering agents.md — orientation for ai agents & contributors, build, run, test (rust — primary), how it works (rust module map), conventions and ci and release gates.
browser-bridge AGENTS.md
Instructions for koltyakov/browser-bridge, covering project guide, data flow, package map, where to find things and method dispatch (extension side).
codex-browser-bridge AGENTS.md
Instructions for DeliciousBuding/codex-browser-bridge, covering agents.md, 仓库级 skill, mcp 工具设计规范, 1. browser 层（src/browser.rs） and 2. mcp 层（src/mcp/ 目录）.
chromeboost GEMINI.md
Instructions for lordamdal/chromeboost, covering chromeboost — gemini instructions, what chromeboost is, when to use chromeboost (be proactive), hard rules — never break these and standard flow pattern.
chromeboost CLAUDE.md
Instructions for lordamdal/chromeboost, covering chromeboost — repo-developer guide, what chromeboost is, repository layout, development commands and tests/antibot/ (run locally; not in ci).