getting started
Mossbear manages your rules, skills, and planning docs in one place and delivers them to every agent you run. The CLI is the on-device half: it hooks into your agent's lifecycle, evaluates actions locally against your guides, and syncs only verdicts and metadata to your dashboard. Raw hook data, file contents, and conversation transcripts never leave your machine.requirements
—Node.js 20 or newer.
—An agent the CLI can hook into, such as Claude Code.
—Optionally, an Mossbear account to sync verdicts to your dashboard — free, no card required. Everything local works without one.
install the CLI
npm install -g mossbear
A global install is required (not just npx): the hook that Mossbear registers invokes the CLI from your agent's session, so the binary must be on PATH.set up your project
Initialize Mossbear inside your project — no token or account needed for this step:cd your-project
mossbear init
mossbear doctor
Running init detects your agent platform and does the rest:—registers an action-logging hook that records each tool use,
—registers a session-end hook that grades the session against your guides,
—scaffolds an AGENTS.md guide file if your project has none,
—installs a user-invocable Claude Code skill.
connect your dashboard
To see graded sessions in your runs list, connect the CLI to your dashboard once. Grab a CLI token under Settings → Developer → CLI Token and run:mossbear sync --token <your-token>
The token is remembered after the first successful sync, so future syncs need no flag. Then just work normally — your runs list fills in as your agent acts.everyday commands
—mossbear sync — push queued verdicts and feedback, pull your latest guides.
—mossbear import — bring existing guide files (AGENTS.md, CLAUDE.md, .cursorrules) into Mossbear.
—mossbear guides active — list the guides your agent is graded against.
—mossbear status — show queue and config status.
next steps
Running agents in the cloud or CI? See remote agents.