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/phkus/tinderbox-mcp/claude-mdgit clone --depth 1 https://github.com/phkus/tinderbox-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/phkus/tinderbox-mcp/claude-md)<a href="https://agentmods.dev/instructions/phkus/tinderbox-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/phkus/tinderbox-mcp/claude-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 5.1 | $0.01106 | $0.01106 |
| Opus 5 | $0.00553 | $0.00553 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
tinderbox-mcp CLAUDE.md scanned grade A 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Script Execution Pipeline**: Uses Node's `child_process.execFile` to call `osascript` with compiled AppleScript files How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Overview
Tinderbox MCP Server is a Model Context Protocol (MCP) server that enables AI assistants to interact with Tinderbox, a macOS knowledge management application. The server uses AppleScript to control Tinderbox documents, allowing AI assistants to create notes, link them, update attributes, and navigate document hierarchies via natural language.
Build and Development Commands
# Install dependencies
npm install
# Build the TypeScript project
npm run build
# Run the server (requires built files)
npm run start
# Run with custom AppleScript directory
node build/index.js /path/to/applescripts
The build output goes to the build/ directory. The server accepts one optional argument: the path to the AppleScript files (defaults to ./applescripts).
Architecture
Core Components
src/index.ts - Single-file architecture containing:
- MCP Server Setup: Creates an MCP server using
@modelcontextprotocol/sdk - Script Registry (
scriptConfigs): Maps tool names to their configurations, including descriptions and Zod parameter schemas - Script Execution Pipeline: Uses Node's
child_process.execFileto callosascriptwith compiled AppleScript files - Security Validation (
validateScriptPath): Ensures scripts are within the allowed directory and have.scptextension
AppleScript Integration
The server bridges MCP tools to AppleScript via a registration system:
- Each entry in
scriptConfigsdefines a tool with its parameters and defaults - The
registerScriptTools()function dynamically registers each configured script as an MCP tool - When a tool is called, parameters are validated with Zod schemas (applying defaults), then converted to
key=valueformat - The corresponding
.scptfile inapplescripts/is executed viaosascript
Available AppleScript Tools:
create_note- Creates notes with title, text, parent pathread_note- Retrieves note title and textget_children- Lists child notes with paths and ChildCountget_siblings- Lists sibling notes at the same hierarchy levelget_links- Returns outgoing links from a notelink_notes- Creates typed links between notesupdate_attribute- Modifies note attributes (WARNING: can overwrite existing content including Name and Text)
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 · 111 lines · 1,106 tokens per session scan A 778f833a1960
tinderbox-mcp CLAUDE.md is an instructions file published in the GitHub repository phkus/tinderbox-mcp (6 stars, last pushed 10mo ago), licensed MIT. It adds 1,106 tokens to every session, about $0.0055 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).