grove

A set of Grove skills for managing multiple isolated coding-agent workspaces and configuring Grove. Workspaces are separate working directories where agents can handle different tasks.

In plain words
What is it for?
Use it to orchestrate agent workspaces, report progress from inside one, configure Grove, or reinstall it when an update fails.
Why use it?
It provides instructions for coordinating agent tasks, tracking their phases, linking tickets and pull requests, and keeping the setup configured.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add bearlike/Grove
agentmods
npx agentmods add plugins/bearlike/grove/marketplace
Clone the repo
git clone --depth 1 https://github.com/bearlike/Grove

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

grove 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 yesterday.

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.

.claude-plugin/marketplace.json · 34 lines

What it actually says

{
  "name": "grove",
  "description": "Grove's own skills, published from the repository that implements them \u2014 orchestrating a fleet of coding-agent workspaces, working inside one, and configuring and updating Grove itself.",
  "version": "1.0.0",
  "owner": {
    "name": "bearlike"
  },
  "plugins": [
    {
      "name": "grove",
      "displayName": "Grove",
      "version": "1.2.0",
      "description": "Grove's own skills, published from the repository that implements them. Four skills: using-grove (orchestrate a fleet of isolated agent workspaces from outside \u2014 CLI verbs, MCP tool ids, ticket and PR linking and the live status comment it turns on), working-in-grove (report task phase from inside a workspace and keep every attached ticket current), configuring-grove (the config cascade, agents, init scripts, containers, ticket providers and the issue-ops mirror), and reinstalling-grove (when an update did not take).",
      "author": {
        "name": "bearlike"
      },
      "category": "Development",
      "keywords": [
        "grove",
        "worktrees",
        "agents",
        "mcp",
        "cli",
        "fleet",
        "phase",
        "tickets",
        "issueops",
        "configuration"
      ],
      "source": "./src/grove"
    }
  ]
}
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.

  1. yesterday First seen · 34 lines scan A c07d7f9ab003

Subscribe to this mod's changes

grove is a plugin published in the GitHub repository bearlike/Grove (2 stars, last pushed 11d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.