Borrowing it
Nothing to install: this file belongs to rcobb2/desktop-management-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/rcobb2/desktop-management-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/rcobb2/desktop-management-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/rcobb2/desktop-management-mcp/claude-md)<a href="https://agentmods.dev/instructions/rcobb2/desktop-management-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rcobb2/desktop-management-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/rcobb2/desktop-management-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rcobb2/desktop-management-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 | $0.23062 | $0.23062 |
| Opus 5 | $0.11531 | $0.11531 |
| Sonnet 5 | $0.04612 | $0.04612 |
| Haiku 4.5 | $0.02306 | $0.02306 |
Grade A, and why
desktop-management-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 7d 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 — 214 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.
Commands
See package.json's scripts block for the exact commands (build/clean/start:jamf/start:intune/test/test:write/test:unit) — start:jamf/start:intune run on ports 3001/3002 respectively (see Architecture below).
Start scripts use Bitwarden Secrets Manager — set BWS_ACCESS_TOKEN in your shell, then run ./start-jamf.sh or ./start-intune.sh. The bws run -- wrapper injects credentials as env vars.
Tests require credentials as env vars (set by BWS or manually) plus TEST_COMPUTER_NAME, TEST_COMPUTER_SERIAL, and TEST_USER_EMAIL for JAMF test fixtures. The package/script/smart-group/policy/configuration-profile write tests (see Tests below) additionally read optional TEST_PACKAGE_PATH, TEST_SCRIPT_NAME, TEST_SMART_GROUP_NAME, TEST_POLICY_NAME, TEST_CONFIG_PROFILE_NAME — each test skips gracefully if its var is unset. The Intune test suite (test/intune-api.test.ts) needs no required fixtures for its read tests; its write tests optionally read TEST_AZURE_GROUP_NAME, TEST_ANDROID_CONFIG_POLICY_NAME, TEST_ANDROID_SETTING_DEFINITION_ID, TEST_ANDROID_SETTING_VALUE, TEST_ANDROID_APP_ID, and TEST_ANDROID_MANAGED_STORE_PACKAGE_ID — same skip-if-unset pattern. Its intune_get_device_groups regression test (see the azureADGroups fix below) optionally reads TEST_INTUNE_DEVICE_NAME/TEST_INTUNE_DEVICE_GROUP_NAME, same pattern.
Architecture
Two standalone Streamable HTTP servers built on Express + @modelcontextprotocol/sdk. Each is single-file and self-contained — helpers like toText/notFound/errorResult/resolveDevice are duplicated per server rather than shared, so a fix in one server file does not propagate to the other:
src/mcp/jamf-server.ts— JAMF MCP server on port 3001.createJamfMcpServer(roles)builds a freshMcpServer+JamfClientper HTTP request (stateless mode, required for load-balanced/APIM deployment), registering only the tools the caller's resolved roles permit; every POST to/mcpgets its ownStreamableHTTPServerTransportwithsessionIdGenerator: undefined, torn down onres.on("close"). Exposes read tools plus write tools (jamf_update_computer,jamf_assign_computers_to_prestage,jamf_flush_mdm_commands,jamf_flush_policy_logs,jamf_create_configuration_profile,jamf_delete_computer,jamf_delete_configuration_profile,jamf_create_extension_attribute).src/mcp/intune-server.ts— Intune MCP server on port 3002. Same per-request stateless transport pattern. Exposes read tools plus write tools (intune_send_device_action,intune_set_device_category,intune_set_device_name,intune_set_autopilot_group_tag,intune_set_autopilot_friendly_name,intune_assign_policy,intune_assign_app,intune_create_win32_app,intune_assign_app_to_groups,intune_create_android_compliance_policy,intune_update_compliance_policy,intune_assign_compliance_policy,intune_create_android_configuration_profile,intune_update_configuration_profile,intune_create_android_app_configuration_policy,intune_update_app_configuration_policy,intune_assign_app_configuration_policy,intune_create_android_managed_store_app,intune_create_remediation,intune_assign_remediation,intune_run_remediation_now).
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.
- 7d ago First seen · 214 lines · 23,062 tokens per session scan A 8ed3a43d88cc
desktop-management-mcp CLAUDE.md is an instructions file published in the GitHub repository rcobb2/desktop-management-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 23,062 tokens to every session, about $0.1153 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 2026-09-01.
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.
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.