What is laptop-care CLAUDE.md?

Repository instructions for laptop-care, a cross-platform MCP server that helps an agent perform laptop maintenance. MCP is a standard way for coding agents to use external tools.

Use it when developing or extending laptop-care, including adding commands, tools, prompts, consent checks, or maintenance workflows.

It explains the project structure, safety controls, platform-specific commands, setup process, and rules for adding maintenance tools.

How malpanishubham2/laptop-care configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to malpanishubham2/laptop-care. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/malpanishubham2/laptop-care/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/malpanishubham2/laptop-care

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/malpanishubham2/laptop-care/claude-md/github.svg)](https://agentmods.dev/instructions/malpanishubham2/laptop-care/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/malpanishubham2/laptop-care/claude-md"><img src="https://agentmods.dev/badge/instructions/malpanishubham2/laptop-care/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/malpanishubham2/laptop-care/claude-md"><img src="https://agentmods.dev/badge/instructions/malpanishubham2/laptop-care/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 742 This file is loaded in full into every session.

When invoked 742 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00742	$0.00742
Opus 5	$0.00371	$0.00371
Sonnet 5	$0.00148	$0.00148
Haiku 4.5	$0.00074	$0.00074

Measured 8d ago against content hash 20164ad3571d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

laptop-care 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 8d 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.

- `src/runner.ts` is the `child_process.exec` wrapper with per-tool timeouts.

CLAUDE.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

laptop-care

Cross-platform laptop maintenance agent, distributed as an MCP server.

Architecture

src/index.ts is the MCP server entry point. Registers tools, prompts, the consent interlock, sequencing gates, and the report card.
src/tools.ts has tool definitions (name, description, safety tier, Zod schema). Add new tools here.
src/commands.ts has platform command strings keyed by darwin | win32. Add new OS commands here.
src/runner.ts is the child_process.exec wrapper with per-tool timeouts.
src/cli.ts is the CLI entry point: setup auto-configs Claude Desktop, help shows usage, default starts the server.
prompts/ holds the agent playbook, split by lifecycle stage so nobody loads instructions they cannot use:
- prompts/kernel.md is pushed on every connect. Identity and non-negotiable safety rules.
- prompts/first-run.md is the onboarding workflow. Loaded only for new users.
- prompts/returning-run.md is the follow-up workflow. Loaded only for returning users.
- prompts/shared.md is judgment rules, escalation thresholds, tone, and report format.
start_maintenance decides first-run vs returning in code (by whether health.csv exists) and sends only the workflow that applies.

Commands

npm run build          # compile TypeScript to dist/
npm run dev            # watch mode
node dist/cli.js       # start MCP server
node dist/cli.js setup # add to Claude Desktop config
node dist/cli.js help  # show help

Adding a new tool

Add the command strings to commands.ts (both darwin and win32)
Add the tool definition to tools.ts (name, description with safety tag, schema)
If the tool needs custom logic (not just running a shell command), add a handler in index.ts and register it in CUSTOM_HANDLERS
Update the relevant file in prompts/ if the tool changes the maintenance workflow
If the tool must run only after another one, add it to REQUIRES in index.ts
npm run build and test

Read the full file on GitHub · 63 lines

Changes

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.

8d ago First seen · 63 lines · 742 tokens per session scan A 20164ad3571d

Subscribe to this mod's changes

laptop-care CLAUDE.md is an instructions file published in the GitHub repository malpanishubham2/laptop-care (0 stars, last pushed 1mo ago), licensed MIT. It adds 742 tokens to every session, about $0.0037 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 2026-09-01.

Hardware and IoT

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

laptop-care: Instructions file for Claude Code