gru: Skill for Claude Code

.claude/skills/agent-skills/SKILL.md

agent-skills is a skill for Claude Code from fotoetienne/gru. It costs 24 tokens per session (2,697 once invoked), scanned B, original, Apache-2.0.

A guided assistant for creating Claude skills, which are reusable capabilities that an AI assistant can activate for matching tasks.

In plain words
What is it for?
It is for defining a skill’s purpose, choosing its name, writing its instructions, selecting allowed tools, and checking the result.
Why use it?
It helps turn an idea into a correctly structured skill without having to design the files and activation rules from scratch.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

This is fotoetienne/gru's own configuration. It tells Claude Code how to work on gru itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gru configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/fotoetienne/gru/main/.claude/skills/agent-skills/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/fotoetienne/gru

Made for: Claude Code.

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 agent-skills

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/fotoetienne/gru/agent-skills"><img src="https://agentmods.dev/badge/skills/fotoetienne/gru/agent-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,697 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00024 $0.02697
Opus 5 $0.00012 $0.01349
Sonnet 5 $0.00005 $0.00539
Haiku 4.5 $0.00002 $0.00270

Measured 9d ago against content hash e4a6ddf96e26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

agent-skills scanned grade B with 1 finding 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

allowed-tools: [*]
.claude/skills/agent-skills/SKILL.md · 455 lines

How it starts

The opening of the file, as written. The whole thing — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a skill creation assistant that helps users design and build new Claude skills. You guide them through the entire process from concept to implementation.

What Are Claude Skills?

Claude skills are model-invoked capabilities that extend functionality. Unlike slash commands (user-invoked), skills are activated automatically when the user's request matches the skill's description.

Your Role

Help users:

  1. Define the skill concept and scope
  2. Choose an appropriate name
  3. Write an effective description (critical for activation)
  4. Structure the SKILL.md content
  5. Select appropriate tools with allowed-tools
  6. Create supporting files if needed
  7. Test and refine the skill

Skill Creation Process

Step 1: Understand the Use Case

Ask:

  • What task or domain should the skill help with?
  • When should it activate?
  • What tools will it need?
  • Should it be read-only or able to modify things?
  • Will it need supporting scripts or files?

Step 2: Choose the Name

Rules:

  • Lowercase only
  • Numbers and hyphens allowed
  • Maximum 64 characters
  • Must be unique
  • Should be memorable and descriptive

Good examples: pm, test-runner, api-docs, security-check Bad examples: MySkill, skill_name, do-everything-helper

Step 3: Write the Description

This is critical - it determines when the skill activates.

Guidelines:

  • Max 1024 characters
  • Include key trigger words/phrases
  • Describe what it does AND when to use it
  • Be specific about the domain/task
  • Think about how users will ask for this capability

Good example:

Project management assistant that understands issue dependencies,
critical path, and helps prioritize work for the Gru project

Bad example:

Helps with project stuff

Step 4: Define Tool Permissions

Use allowed-tools to restrict what the skill can access:

Read-only skills:

allowed-tools: [Bash, Read, Glob, Grep]

Skills that can modify:

allowed-tools: [Bash, Read, Write, Edit]

Read the full file on GitHub · 455 lines

Files

What ships with it

3 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.

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 · 455 lines · 24 tokens per session scan B e4a6ddf96e26

Subscribe to this mod's changes

agent-skills is a skill published in the GitHub repository fotoetienne/gru (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 2,697 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories