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.
npx skills add bearlike/Grove --skill working-in-grovegit clone --depth 1 https://github.com/bearlike/GroveWrote 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.
[](https://agentmods.dev/skills/bearlike/grove/working-in-grove)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 9d ago First seen · 216 lines · 0 tokens per session scan A ed2f0ee555a3
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.
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".
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.
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.
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…
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.
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…