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/ggprompts/tabzchrome/agents-mdgit clone --depth 1 https://github.com/GGPrompts/TabzChromeWrote 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/ggprompts/tabzchrome/agents-md)<a href="https://agentmods.dev/instructions/ggprompts/tabzchrome/agents-md"><img src="https://agentmods.dev/badge/instructions/ggprompts/tabzchrome/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 | $0.00427 | $0.00427 |
| Opus 5 | $0.00214 | $0.00214 |
| Sonnet 5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00043 | $0.00043 |
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 5d 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.
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:8129and 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
/rebuildto build the extension (do not usenpm run build) - Start backend with
./scripts/dev.sh(orcd backend && npm start) - Run tests with
npm test -- --run
Documentation Updates
- Update
CHANGELOG.mdfor user-visible changes - Add lessons to
docs/lessons-learned/for tricky bugs - Update
CLAUDE.mdonly 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.
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.
- 5d ago First seen · 56 lines · 427 tokens per session scan A 9a820e7c9fe9
TabzChrome AGENTS.md is an instructions file published in the GitHub repository GGPrompts/TabzChrome (146 stars, last pushed 11d ago), licensed MIT. It adds 427 tokens to every session, about $0.0021 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 2026-08-30.
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.