Borrowing it
Nothing to install: this file belongs to istefox/istefox-dt-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/istefox/istefox-dt-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/istefox/istefox-dt-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/istefox/istefox-dt-mcp/claude-md)<a href="https://agentmods.dev/instructions/istefox/istefox-dt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/istefox/istefox-dt-mcp/claude-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.
<a href="https://agentmods.dev/instructions/istefox/istefox-dt-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/istefox/istefox-dt-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02309 | $0.02309 |
| Opus 5 | $0.01154 | $0.01154 |
| Sonnet 5 | $0.00462 | $0.00462 |
| Haiku 4.5 | $0.00231 | $0.00231 |
Grade A, and why
istefox-dt-mcp CLAUDE.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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — DEVONthink MCP Connector
Istruzioni di progetto. Sovrascrivono il default e si aggiungono alle regole globali in
~/.claude/CLAUDE.md.
1. Identità del progetto
- Nome interno:
istefox-dt-mcp - Scopo: MCP server "best-in-class" per DEVONthink 4 — dual-transport, multi-bridge, RAG-augmented
- Owner: Stefano Ferri (progetto personale, namespace
istefox— non lavorativo) - Documento di architettura di riferimento:
/Users/stefanoferri/Downloads/ARCH-BRIEF-DT-MCP.md(versione 0.1, 29/04/2026) - Stato attuale: brief approvato, in attesa di review architetturale Cowork → ADR finale → implementazione
Quando in dubbio sull'architettura, riferirsi al brief, non improvvisare.
2. Vincoli OBBLIGATORI di progetto (non negoziabili)
2.1 Vincoli legali / IP
- Implementazione clean-room: NON guardare, NON copiare, NON ispirarsi al codice di
dvcrn/mcp-server-devonthink(GPL-3.0). Concept ok, codice mai. - Privacy by design: nessun dato dell'utente esce dalla macchina per default. Embedding, audit log, cache: tutto locale.
2.2 Vincoli protocollo MCP
- stdio mode: MAI scrivere su
stdout. Corrompe il flusso JSON-RPC. Logging solo sustderro file. - Schema first: ogni tool deve avere schema JSON Schema rigoroso via Pydantic v2.
- Tool description ≤ 2KB, server instructions ≤ 2KB (limite Claude Code).
- Resource URI stabili e deterministici (
dt://...). - Resource bounded: ogni resource ≤ 25K token (limite Claude Code default). Mai dump di interi database.
- Tool naming: nomi compatti, contesto nelle description.
2.3 Vincoli DEVONthink
- DT4-first: target primario
Application("DEVONthink")(DT4). DT3 è best-effort opzionale con feature gating. - DT Pro deve essere in esecuzione per il bridge JXA (eccetto bridge DT Server).
- JXA è single-threaded: necessario worker pool con semaphore + backpressure (default 4-8 worker concorrenti, timeout 5s).
- Sync sidecar: smart rule DT → sidecar + reconciliation notturno hash-based. NO filesystem watching su
~/Library/Application Support/DEVONthink/(inaffidabile). - DB vector fuori dalla cartella DEVONthink (evita lock contention).
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.
- 10d ago First seen · 167 lines · 2,309 tokens per session scan A 8de3025dfd2e
istefox-dt-mcp CLAUDE.md is an instructions file published in the GitHub repository istefox/istefox-dt-mcp (14 stars, last pushed 3mo ago), licensed MIT. It adds 2,309 tokens to every session, about $0.0115 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
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.
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.
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).
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.