Questions, answered.

Claude Code is Anthropic's AI assistant that works directly with the files and tools on your computer. It can read and write documents and code, run commands, and connect to your other tools, asking for your approval along the way. It comes with Claude Pro, Max, Team and Enterprise plans.

Claude Cowork is the part of the Claude desktop app that does multi-step work for you: research, drafting, working with your files and connected apps such as email or a CRM, and recurring scheduled tasks. On Pro and Max plans, new Cowork tasks run in Claude's cloud; Cowork can work in a folder on your PC while the desktop app is open.

Four steps. A short interview about your work and tools. A check of your PC that changes nothing and reports in plain words. The setup itself: safe approval settings, your API keys moved into an encrypted vault, one work folder chosen on purpose, and instructions written for how you work, with a backup and an undo for every change. Then we verify it works and you get a written receipt. The app does it for you, or a consultant does it with you on a call.

You get Claude doing real work sooner, with less risk and no need to become an expert in its settings. Your keys stay out of plain text files, approval settings are chosen on purpose, you get skills that fit your work, and for Claude Code a weekly check catches it when an update or a new tool changes your setup. Your team gets one standard way of working, and you get a record of what was set up and why.

Using only Cowork: Cowork Setup ($149, or $499 done with you), no monthly plan. Using Claude Code on your own: Setup plus Run ($19 a month, setup $249 per person, waived on annual). A team of 3 or more: Setup plus Govern ($249 setup and $29 a month per person) for one standard setup and a team view. Want it set up once and to manage it yourself: Setup only ($349 per PC). Want a person with you: done with you ($999 for the first PC).

ClevSkill is built for Claude Code and Claude Cowork on Windows. The encrypted vault already works with any program: it can launch other tools with their API keys injected, so keys stay out of plain text files. A read-only check for OpenAI's Codex CLI and GitHub Copilot CLI (keys in plain text, connector config, settings) is coming after the Claude product is complete.

Claude Code updates often, and the tools, MCP servers and keys around it change too. A setup that was right last month can drift without anyone noticing. A Run or Govern plan re-checks your setup every week and after each Claude update, alerts you when something changes, and fixes what it safely can with your OK. Cowork does not need a plan: its tasks run in Claude's cloud, so a Cowork Setup includes a re-check on day 30 instead.

Yes, that's exactly who we built it for. You bring a Claude subscription from Anthropic; Clevskill sets up your desktop the way an expert would and keeps it that way. You never touch a terminal.

They stay, and they get covered. Setup starts with Detect, which inventories what's already on the machine. Your own skills get the same weekly health checks ours do; your configs, memory files, and key storage get scanned for problems; and nothing changes without a backup snapshot first and your approval. If something unusual in your setup is intentional, mark it as an exclusion and it stops being flagged, visibly, never silently.

Yes. The installer has a Repair mode: a read-only diagnostic first scans your setup (skills, configs, MCP servers, memory bloat, secrets posture, costs, usage quota, supply-chain risk in foreign skills, deprecated model ids, version drift, safety hooks, machine and OS checks, Claude auth, third-party packs, and a reconcile pass that inventories your own skills without removing them), shows you exactly what's wrong, and fixes it with your approval. Your files, projects, and history stay untouched; a backup is taken before any change.

Your Claude Code and Claude Cowork desktop installations: setup, curated skills, safety guards, encrypted keys, usage-cost hygiene, and ongoing health monitoring. We never proxy or resell tokens.

Every command the AI runs passes through the guard: catastrophic operations are blocked outright, ordinary deletes are snapshotted to a backup folder first with one-command restore, and every decision is logged with a timestamp. The audit log shows exactly what the AI did and didn't do. The guard significantly reduces the risk of accidental file loss, though no software can guarantee zero risk from all possible actions.

Partially. Claude Cowork asks before permanently deleting files, which is good. ClevSkill goes further: we back up BEFORE any destructive operation runs (so mistakes are reversible with one command, not just refusable), and we keep a tamper-evident local audit log of the agent's tool calls in Claude Code.

Minutes per desktop. The installer detects your current setup, installs your pack, wires the safety hooks, and verifies the result before it says done.

One installed machine. Your license encodes the seat count; add or remove desktops any time from your dashboard.

The subscription isn't access to skills, it's keeping them working. Claude updates regularly and setups break; subscribers get continuous skill updates, the weekly health scan, one-click repair, the monitoring dashboard, sync between computers on demand, and support. A setup-only purchase configures your machine the safe way and leaves you the free safety pack to keep; the managed (paid) catalog, updates, and monitoring come with a subscription.

Your license expires at the end of the period. Your files, your own skills, the free safety pack, and your Claude subscription stay put. What stops is what the subscription provides: updates, the weekly Doctor, repair, monitoring, and sync. The managed (paid) pieces are then removed: you export your vault keys (the app walks you through it) and run the uninstaller, which backs everything up reversibly first. We never hold a copy of your keys, so export them before you go.

Export your vault keys first: use the Vault app's 'move my secrets to another PC', or clevskill-vault export, and keep that bundle somewhere safe. The uninstaller then reversibly backs up and removes the ClevSkill products (the paid skills, the guard, the Doctor, monitoring). Your files, projects, your own skills, and your Claude subscription are untouched. We never hold a copy of your keys, so we cannot recover them for you.

In an encrypted vault on your own machine, with the master key in your OS keychain. A copy of your license also lives on your account page. Neither is ever sent anywhere else.

Only the scoreboard: finding counts and titles from the weekly health scan, engine version, and a timestamp. Never file contents, configs, keys, or chat history. It is opt-in at enrollment.

Your own. ClevSkill runs on your Claude subscription (your auth plan). If your subscription hits a problem, the Doctor diagnoses it and the AI automatically falls back to your API key so work doesn't stop. You bring the plan; we never proxy or resell tokens. And we never see or store your API key, it stays in the encrypted vault on your own computer.