Agent Plugins

Claude Code plugins

Engineering context from LinearB, right inside your AI coding agent.

Plugins that give your agent the context a senior engineer would have: how healthy the repo is, how fragile the files are, and how much care the change deserves.

/plugin marketplace add linear-b/agent-plugins
Browse pluginsWhat's new

Quick start

  1. Add the marketplace

    In Claude Code, run /plugin marketplace add linear-b/agent-plugins.

  2. Install a plugin

    For example /plugin install agentic-advisor@linearb-ai.

  3. Connect LinearB

    Create a token in LinearB → Settings → API Tokens, export LINEARB_API_TOKEN=…, then restart Claude Code.

Roll out to your whole org

Admins can install and enable this for every developer from Claude.ai admin console → Claude Code → Managed settings. Paste this, then replace the token placeholder.

The token in managed settings is pushed to every developer's machine. Use a token created for this purpose, so you can rotate it on its own.

{
  "env": {
    "LINEARB_API_TOKEN": "<token from LinearB > Settings > API Tokens>"
  },
  "extraKnownMarketplaces": {
    "linearb-ai": {
      "source": {
        "source": "github",
        "repo": "linear-b/agent-plugins"
      },
      "autoUpdate": true
    }
  },
  "enabledPlugins": {
    "agentic-advisor@linearb-ai": true
  }
}

Plugins

agentic-advisor

v1.3.0

Before writing code, grades how fragile the target is from LinearB health signals + local git history and holds the agent to a matching effort level (LOW/MEDIUM/HIGH) — lean on calm repos, defensive on fragile ones.

Updated
/plugin install agentic-advisor@linearb-ai
Read the docsChangelog

What's new

  • agentic-advisor 1.3.0

    The troubleshooting log is now on by default, so a missing event can be diagnosed without asking the user to re-run anything. Turn it off with LINEARB_DEBUG=0. It stays local and private (0600), rotates at 1 MB, and never contains the token, prompt or payload.

  • agentic-advisor 1.2.0

    Ticket context: when the prompt or branch names a ticket (e.g. ABC-123), the skill fetches its type, priority, estimate and labels from LinearB (one call, same token) and uses them to raise the task-complexity grade, e.g. a Highest-priority bug. Skipped silently when there's no key or no PM integration.

  • agentic-advisor 1.1.2

    Opt-in troubleshooting log: LINEARB_DEBUG=1 writes each report's outcome (skip reason or HTTP status) to ${XDG_CACHE_HOME:-~/.cache}/agentic-advisor/report.log, rotated at 1 MB. Lines for sent events include the grade and repo name; no line contains the token, email, prompt or payload. The log stays private (folder 0700, file 0600, symlinked logs and rotation targets refused).

Full changelog →

Built to stay out of the way

Your data stays in your org
Usage is reported only to the LinearB org your token belongs to. Source code and full prompts are never sent.
Never blocks
If LinearB can't be reached, plugins fall back to safe defaults and your agent keeps working.
Open source
Apache-2.0. Report vulnerabilities to security@linearb.io, per SECURITY.md.