What is TabzChrome AGENTS.md?

A project instruction file for GGPrompts and TabzChrome, covering the codebase, development rules, build and test commands, and documentation practices. The project includes a Chrome side panel, a Node.js backend, and an MCP server.

It is for guiding development, specifying how to build and test the project, managing tracked work with ggbd, and recording user-visible changes or lessons learned.

It gives coding agents shared context and rules, reducing the chance of breaking protocols, storage formats, platform support, or project routines.

How GGPrompts/TabzChrome configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to GGPrompts/TabzChrome. 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/GGPrompts/TabzChrome/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/GGPrompts/TabzChrome

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ggprompts/tabzchrome/agents-md/github.svg)](https://agentmods.dev/instructions/ggprompts/tabzchrome/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ggprompts/tabzchrome/agents-md"><img src="https://agentmods.dev/badge/instructions/ggprompts/tabzchrome/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ggprompts/tabzchrome/agents-md"><img src="https://agentmods.dev/badge/instructions/ggprompts/tabzchrome/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 427 This file is loaded in full into every session.

When invoked 427 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.

Model	Per session	Once invoked
Fable 5.1	$0.00427	$0.00427
Opus 5.5	$0.00171	$0.00171
Sonnet 5.5	$0.00085	$0.00085
Haiku 4.5	$0.00043	$0.00043

Measured 2mo ago against content hash 9a820e7c9fe9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

TabzChrome 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 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.

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 · 56 lines

What it actually says

Agent Instructions

This project uses ggbd (beads) for issue tracking with a shared Supabase/Postgres backend.

Project Context

Chrome extension side panel + Node.js backend + MCP server
Backend runs on localhost:8129 and uses tmux for sessions
Bash-only terminals; avoid adding other shell types

Development Rules

Keep it simple; avoid over-engineering
Cross-platform only: no hardcoded paths or OS-specific assumptions
Do not break WebSocket protocol or Chrome storage schema
Avoid adding new npm dependencies unless absolutely necessary

Build & Test

Use /rebuild to build the extension (do not use npm run build)
Start backend with ./scripts/dev.sh (or cd backend && npm start)
Run tests with npm test -- --run

Documentation Updates

Update CHANGELOG.md for user-visible changes
Add lessons to docs/lessons-learned/ for tricky bugs
Update CLAUDE.md only for architecture changes

Quick Reference

ggbd ready              # Find available work
ggbd show <id>          # View issue details
ggbd update <id> --status in_progress  # Claim work
ggbd close <id>         # Complete work
# Supabase auto-syncs (no manual sync needed)

Landing The Plane (When Shipping)

Only do this workflow when asked to land changes (commit/push), or when finishing a change that should clearly be published.

File ggbd issues for follow-ups (only if needed)
Run relevant quality gates (tests/linters/build) if applicable
Update/close ggbd issue(s) if used

Publish:

git pull --rebase
git push
git status  # should show "up to date with origin"

Hand off: brief context for next session

If not shipping, leave a clear handoff summary instead.

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.

2mo ago First seen · 56 lines · 427 tokens per session scan A 9a820e7c9fe9

Subscribe to this mod's changes

TabzChrome AGENTS.md is an instructions file published in the GitHub repository GGPrompts/TabzChrome (149 stars, last pushed 1mo ago), licensed MIT. It adds 427 tokens to every session, about $0.0017 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.

TabzChrome AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
TabzChrome AGENTS.mdGGPrompts/TabzChrome	Instructions file	149	1mo ago	MIT	A	427	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

TabzChrome: Instructions file for Codex