working-in-grove

working-in-grove is a skill for Claude Code from bearlike/Grove. It costs 197 tokens per session (2,457 once invoked), scanned A, original, MIT.

Instructions for a coding agent working inside a Grove workspace, which is an isolated project copy created for one task. They explain how to report the workspace phase, progress, task list, findings, and delivery status.

In plain words
What is it for?
Use them while working on a Grove-assigned task to keep phase and progress information current. They cover workspace naming, progress reporting, task checklists, and communicating confirmed causes, fixes, or pull requests.
Why use it?
They make the agent's state visible to whoever manages the fleet without requiring someone to inspect the workspace directly. They also separate short status updates from detailed ticket comments.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the grove plugin — 4 skills shipped together

Good fit Use them while working on a Grove-assigned task to keep phase and progress information current. They cover workspace naming, progress reporting, task checklists, and communicating confirmed causes, fixes, or pull requests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bearlike/grove/working-in-grove
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.

Any agent
npx skills add bearlike/Grove --skill working-in-grove
Clone the repo
git clone --depth 1 https://github.com/bearlike/Grove

Made for: Claude Code.

Or install grove, the plugin that ships this one along with the rest of its 4 skills.

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.

agentmods badge for working-in-grove

README.md
[![agentmods](https://agentmods.dev/badge/skills/bearlike/grove/working-in-grove/github.svg)](https://agentmods.dev/skills/bearlike/grove/working-in-grove)
Your own site
<a href="https://agentmods.dev/skills/bearlike/grove/working-in-grove"><img src="https://agentmods.dev/badge/skills/bearlike/grove/working-in-grove/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.

agentmods 80×15 button for working-in-grove

Your own site · 80×15
<a href="https://agentmods.dev/skills/bearlike/grove/working-in-grove"><img src="https://agentmods.dev/badge/skills/bearlike/grove/working-in-grove.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 197 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,457 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00197 $0.02457
Opus 5 $0.00098 $0.01229
Sonnet 5 $0.00039 $0.00491
Haiku 4.5 $0.00020 $0.00246

Measured 9d ago against content hash ed2f0ee555a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

working-in-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 9d 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.

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.

src/grove/skills/working-in-grove/SKILL.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working inside a Grove workspace

You are one agent in a fleet. Somebody is watching twenty workspaces at once and cannot attach to yours to find out how it is going. Report your task phase so they can tell scoping from delivery at a glance.

What becomes public

When a ticket is attached and issue-ops is enabled, Grove keeps one live sticky comment on that ticket. It shows the workspace status, branch and commit, your reported phase and note, current activity, todo checklist, and other attached refs. Anyone who can read the ticket can read this comment.

Keep the note and active-task text short and human-readable; raw tool output, another agent's message, or harness markup is published verbatim. The mirror says where you are, not what you found: write a real ticket comment when you confirm a cause, land a fix, or open a pull request.

If nothing about your work should be public, raise that with whoever created the workspace; do not silently stop reporting. If you are instead DRIVING a fleet, use using-grove. For installation configuration, use configuring-grove.

Keep the todo list current

Create the list on your first turn, before your first edit. Give every meaningful piece of work its own item: a discovery, a code change, a verification step, or a delivery step. Do not turn individual commands or files into items unless they are independently useful to the person reading the list.

Mark an item complete as soon as that piece of work is complete. Keep exactly one item in progress; move to the next only after completing or deliberately superseding the current one. This is not private scratch planning: Grove renders the list as the public checklist on every attached ticket. An empty list says there is no plan, and stale items say work remains when it does not.

Name the workspace

If its title is a generated id or its description is empty, set both once you understand the task. Somebody is reading this name to tell your workspace from twenty others.

Read the full file on GitHub · 216 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.

  1. 9d ago First seen · 216 lines · 0 tokens per session scan A ed2f0ee555a3

Subscribe to this mod's changes

working-in-grove is a skill published in the GitHub repository bearlike/Grove (2 stars, last pushed 18d ago), licensed MIT. It adds 197 tokens to every session and 2,457 once invoked, about $0.0010 per session on Opus 5. 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.

Related

Other skills, from other repositories

fr-dispatch

Queue a plan's phases to a runner (fr apply --to ) and reconcile its GitHub Issues. Use when: "dispatch this plan", "send to VK", "create issues from plan", "sync plan to GitHub".

derio-net/super-fr · 54 tokens

parallel-execution-strategy

Use when 3+ independent tasks are ready in .forge/tasks.yaml and multiple agents will work concurrently, when assessing file-conflict risk before dispatching parallel work, when planning branch and merge sequencing for a sprint, or when prior parallel runs have caused merge nightmares.

aneja5/forge-skills · 59 tokens

git-workflow

Use when committing work, creating branches, preparing PRs, resolving merge conflicts, when grouping related changes into commits, when cleaning up history before merging, or when deciding what should be a separate commit vs squashed.

aneja5/forge-skills · 47 tokens

pipeline-conductor

Operating procedure for the kirocrew-pipeline-conductor agent - run one issue/PR pipeline on one repository as a supervised fleet. Auto-pick items, preflight every candidate to one deterministic claim verdict, stand up one worker session per item in a dedicated folder, probe them each cycle with one script call…

kirodotdev/KiroCrew · 142 tokens

github

Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.

AtomicBot-ai/atomic-agent · 48 tokens

gh

GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, or (6) Perform any GitHub…

bubbuild/bub · 87 tokens