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/amingclawdev/toolboxclient/agents-mdgit clone --depth 1 https://github.com/amingclawdev/toolBoxClientWhat 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 | $0.00952 | $0.00952 |
| Opus 5 | $0.00476 | $0.00476 |
| Sonnet 5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
toolBoxClient 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- toolBoxClient CLAUDE.md — 92% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
Build & Dev Commands
# Development
npm start # React dev server (port 3000)
npm run dev # Electron + backend (dev mode, IS_BUILD=false)
# Build
npm run build # React production build (react-app-rewired)
npm run dist # Electron distributable (electron-builder)
# Tests
npm run test # Client tests (Jest + React Testing Library)
npm run test:server # Server tests (Jest, Node environment)
npm run test:all # Both client and server
npm run test:e2e # Playwright end-to-end tests
# Run a single test file
npx jest path/to/file.test.js # server tests
npx react-app-rewired test --watchAll=false -- path/to/file.test.js # client tests
Architecture
Electron desktop app with three layers communicating via HTTP + WebSocket:
Electron Main (electron.js + preload.js)
├─ React Frontend (client/src/, port 3000)
│ Uses: React 18, React Bootstrap, Zustand, i18next
└─ Express Backend (server/, port 30001)
Uses: Express, express-ws, NeDB (embedded DB)
- Electron main process (
electron.js): Window management, IPC for native dialogs, spawns backend - React client (
client/src/): UI layer, communicates with backend viautils/api.js(Axios, base/api) andutils/webSocket.js(real-time task updates) - Express server (
server/): REST API + WebSocket server, spawns Node child processes for task execution
Key data flow
Tasks are defined as configs, executed by server/services/taskService.js which spawns child processes using bundled Node.js (assets/node_for_win/ or assets/node_for_mac/). Real-time execution logs flow back via WebSocket to the React UI.
State Management
Three Zustand stores in client/src/store/:
walletStore.js— wallet listfingerPrintStore.js— browser fingerprint profiles (object keyed by ID)pathStore.js— file paths (chromePath, savePath, scriptDirectory)
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.
- 2d ago First seen · 93 lines · 952 tokens per session scan A 51b071648447
toolBoxClient AGENTS.md is an instructions file published in the GitHub repository amingclawdev/toolBoxClient (286 stars, last pushed 5mo ago), licensed MIT. It adds 952 tokens to every session, about $0.0048 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.