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/agent-skills/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/agent-skills)<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.
<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>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 | $0.00024 | $0.02697 |
| Opus 5 | $0.00012 | $0.01349 |
| Sonnet 5 | $0.00005 | $0.00539 |
| Haiku 4.5 | $0.00002 | $0.00270 |
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: [*] 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:
- Define the skill concept and scope
- Choose an appropriate name
- Write an effective description (critical for activation)
- Structure the SKILL.md content
- Select appropriate tools with
allowed-tools - Create supporting files if needed
- 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]
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.
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 · 455 lines · 24 tokens per session scan B e4a6ddf96e26
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.
Other skills, from other repositories
duckduckgo-search
Free keyless web, news, and image search via ddgs.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…