Borrowing it
Nothing to install: this file belongs to Marco-Lelli/legacy-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/Marco-Lelli/legacy-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/Marco-Lelli/legacy-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/marco-lelli/legacy-mcp/claude-md)<a href="https://agentmods.dev/instructions/marco-lelli/legacy-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/marco-lelli/legacy-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/marco-lelli/legacy-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/marco-lelli/legacy-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 | $0.03117 | $0.03117 |
| Opus 5 | $0.01558 | $0.01558 |
| Sonnet 5 | $0.00623 | $0.00623 |
| Haiku 4.5 | $0.00312 | $0.00312 |
Grade A, and why
legacy-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 9d 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 — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LegacyMCP — CLAUDE.md
What this project is
LegacyMCP is a Model Context Protocol (MCP) server for on-premises Active Directory. It exposes AD data as tools that Claude and other LLMs can query directly — enabling AI-powered assessment of any Active Directory environment.
The project is open source (MIT license) with a proprietary enterprise layer maintained by Impresoft 4ward. The open boundary follows the scope of Carl Webster's ADDS_Inventory.ps1 (https://github.com/CarlWebster/Active-Directory-V3).
Repository: https://github.com/Marco-Lelli/legacy-mcp Author: Marco Lelli, Head of Identity — Impresoft 4ward (https://www.4ward.it) Blog: https://legacythings.it
Repository Structure
legacy-mcp/ ├── collector/ # PowerShell offline data collector │ ├── Collect-ADData.ps1 │ ├── README.txt │ └── modules/ # PS helper modules per AD area ├── config/ # config templates for profiles A / B / C ├── docs/ # architecture and documentation ├── installer/ # PowerShell installer and permission scripts │ ├── Setup-LegacyMCP.ps1 # unified installer/configurator (Profile A, B, C) │ ├── mcp-remote-live.ps1 # consultant client runtime script (source, in repo) │ │ # .legacymcp-key, mcp-remote-live.bat and certs/ are generated │ │ # in %LOCALAPPDATA%\LegacyMCP\ -- not in the repository │ ├── modules/ # PS functional modules │ │ ├── LegacyMCP.Common.psm1 │ │ ├── LegacyMCP.Python.psm1 │ │ ├── LegacyMCP.Service.psm1 │ │ ├── LegacyMCP.Certs.psm1 │ │ ├── LegacyMCP.Config.psm1 │ │ ├── LegacyMCP.Client.psm1 │ │ ├── LegacyMCP.Gui.psm1 │ │ ├── LegacyMCP.Gui.Steps.psm1 │ │ └── LegacyMCP.Gui.Exec.psm1 │ └── tools/ # bundled binaries (nssm.exe) ├── src/legacy_mcp/ # MCP server — Python │ ├── server.py # FastMCP entrypoint │ ├── config.py # YAML config loader and validation │ ├── config_registry.py # Windows registry read/write (DPAPI, install config) │ ├── auth.py # ASGI middleware — API key validation (Profile B) │ ├── oauth.py # OAuth 2.0 stub — discovery, PKCE, client_credentials │ ├── workspace/ # scope and connector management │ ├── modes/ # live.py and offline.py │ ├── storage/ # JSON → SQLite ingestion and query helpers │ ├── tools/ # MCP tool registration (one file per AD area) │ │ ├── workspace_info.py │ │ ├── forest.py │ │ ├── domains.py │ │ ├── dcs.py │ │ ├── sysvol.py │ │ ├── sites.py │ │ ├── users.py │ │ ├── groups.py │ │ ├── computers.py │ │ ├── ous.py │ │ ├── gpo.py │ │ ├── trusts.py │ │ ├── fgpp.py │ │ ├── dns.py │ │ ├── pki.py │ │ ├── snapshot.py │ │ ├── snapshot_jobs.py │ │ └── fsp.py │ ├── eventlog/ # Windows EventLog writer │ └── service/ # Windows Service wrapper ├── status/ # session state and project tracking (ST-*.md) └── tests/ ├── fixtures/ # contoso-sample.json (synthetic AD for tests) ├── unit/ └── integration/
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.
- 9d ago First seen · 338 lines · 3,117 tokens per session scan A 2d8633f1a08b
legacy-mcp CLAUDE.md is an instructions file published in the GitHub repository Marco-Lelli/legacy-mcp (0 stars, last pushed 26d ago), licensed MIT. It adds 3,117 tokens to every session, about $0.0156 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 2026-08-31.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.