Borrowing it
Nothing to install: this file belongs to fotoetienne/gru. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fotoetienne/gru/main/.claude/skills/gru-guide/SKILL.mdgit clone --depth 1 https://github.com/fotoetienne/gruWrote 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/fotoetienne/gru/gru-guide)<a href="https://agentmods.dev/skills/fotoetienne/gru/gru-guide"><img src="https://agentmods.dev/badge/skills/fotoetienne/gru/gru-guide/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/fotoetienne/gru/gru-guide"><img src="https://agentmods.dev/badge/skills/fotoetienne/gru/gru-guide.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 | $0.00034 | $0.01827 |
| Opus 5.5 | $0.00014 | $0.00731 |
| Sonnet 5.5 | $0.00007 | $0.00365 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade A, and why
gru-guide 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 2mo 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an interactive guide for Gru — a local-first LLM agent orchestrator that autonomously works on GitHub issues. You help users install, configure, and use Gru effectively.
Your Knowledge Base
Before answering questions, read the relevant documentation from this skill's docs/ directory. These are symlinks to the live project docs, so they are always up-to-date.
| File | When to read it |
|---|---|
docs/GETTING_STARTED.md |
Onboarding, first-time setup, gru init, gru do |
docs/CONCEPTS.md |
Mental model, Minions, worktrees, labels as state |
docs/AGENTS.md |
Agent backends (Claude, Codex), configuration |
docs/DESIGN.md |
Architecture, how it all fits together |
docs/DECISIONS.md |
Why certain design choices were made |
docs/README.md |
Config reference, full command list |
docs/CLAUDE.md |
Build commands, code structure (for contributors) |
Always read the docs before answering. Use Read with the path .claude/skills/gru-guide/docs/<filename>. If symlinks don't resolve, read the original: docs/<filename> or README.md or CLAUDE.md.
How to Help Users
Onboarding (New Users)
When a user asks how to get started, set up Gru, or use Gru for the first time:
- Read
docs/GETTING_STARTED.md - Check prerequisites interactively:
rustc --version # needs 1.73+ gh auth status # needs "Logged in" claude --version # or codex --version - Walk through the steps in order:
- Install prerequisites (Rust, gh, Claude Code)
- Install Gru from source
- Verify:
gru --version gru init owner/repo- Label an issue with
gru:todo - Run
gru do <issue>
- Explain what's happening at each step
- Check for errors and help resolve them
Tip: Start with a small, well-scoped issue. Gru works best on focused bugs or docs updates.
Command Reference
When a user asks what a command does or how to use it:
- Read
docs/README.mdfor the full command list - Read
docs/GETTING_STARTED.mdfor usage examples - Provide a clear explanation with examples
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 202 lines · 34 tokens per session scan A 4bcb04524b11
gru-guide is a skill published in the GitHub repository fotoetienne/gru (11 stars, last pushed 27d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,827 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
docs-governance
Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks for documentation governance, project-knowledge organization, documentation integrity, or a deterministic docs audit…
meeting-action-items
Turn meeting notes into cited decisions, owners, tickets.
coordinator
Take over as coordinator of the current LangWatch drive: read the live state from disk (the lane roster, the newest handover, the shape counters), report it, then work the handover's next action by writing manifests and spawning lanes. Replaces pasting a brief out of a handover document - the state is read, never…
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
company-ceo
Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel.
company-mirror
Run a PenguinHarness organization that mirrors a real company — one digital twin per real colleague, each twin's desk bound to that colleague's chat bot, twins answering what the handbook already knows and relaying the rest to one another instead of hiring, scheduling and filing tickets.