marvin-template: Command for Claude Code

.claude/commands/skills.md

skills is a command for Claude Code from SterlingChin/marvin-template. It costs 13 tokens per session (471 once invoked), scanned A, original, MIT.

A command interface for searching, viewing, installing, and updating coding-agent skills from the skills.sh ecosystem. Skills are add-ons that give an agent instructions for particular tasks.

In plain words
What is it for?
Use it to list installed skills, search for a skill by keyword, install a selected package with confirmation, or update installed skills.
Why use it?
It gathers skill management into a small set of commands instead of requiring separate tools or manual browsing.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is SterlingChin/marvin-template's own configuration. It tells Claude Code how to work on marvin-template 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 marvin-template configures →

About the project

MARVIN is a personal AI assistant built to remember conversations, track goals, organize work, and connect to external applications. People use it as a chief-of-staff-style extension for Claude Code or GitHub Copilot CLI, with integrations including Google Workspace, Microsoft 365, Slack, Linear, Notion, and Telegram. The catalogue entries provide commands, agents, skills, and instructions that define MARVIN's workflows.

SterlingChin/marvin-template · 1,017 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to SterlingChin/marvin-template. 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/SterlingChin/marvin-template/main/.claude/commands/skills.md
Clone the repo
git clone --depth 1 https://github.com/SterlingChin/marvin-template

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 skills

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/sterlingchin/marvin-template/skills"><img src="https://agentmods.dev/badge/commands/sterlingchin/marvin-template/skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 471 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 $0.00013 $0.00471
Opus 5 $0.00006 $0.00235
Sonnet 5 $0.00003 $0.00094
Haiku 4.5 $0.00001 $0.00047

Measured 9d ago against content hash 70c9bc4ca245, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

skills 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.

.claude/commands/skills.md · 80 lines

What it actually says

/skills - Skill Discovery

Manage and discover agent skills from the open skills ecosystem.

Argument: $ARGUMENTS (expects a sub-command: list, search <query>, install <package>, update)

Sub-Commands

No argument / help

Show available sub-commands:

/skills list           Show installed skills
/skills search <query> Search the skills.sh ecosystem
/skills install <pkg>  Install a skill (with confirmation)
/skills update         Check for and apply skill updates

list

Show currently installed skills.

npx skills list 2>/dev/null || echo "Skills CLI not found. Install with: npm i -g skills"

Present results grouped by scope (global vs project-level).

search <query>

Search the skills.sh ecosystem for skills matching the query.

npx skills find <query>
  1. Parse results into a clean list: skill name, description, install command
  2. Present numbered options
  3. Ask: "Want me to install any of these?"
  4. If yes, run the install flow below

install <package>

Install a skill with confirmation.

  1. Show the skill name and package identifier
  2. Link to the skills.sh page if available: https://skills.sh/<owner>/<repo>/<skill>
  3. Ask: "Install this skill? (y/n)"
  4. On confirmation:
    npx skills add <package> -g -y
    
  5. Confirm success or report errors

update

Check for and apply skill updates.

npx skills check

If updates are available:

  1. List skills with available updates
  2. Ask: "Update all, or pick specific ones?"
  3. Run:
    npx skills update
    

Notes

  • Browse skills visually at https://skills.sh
  • Skills install to ~/.agents/skills/ (global) or .agents/skills/ (project)
  • The find-skills skill enables proactive skill suggestions during normal conversation
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 · 80 lines · 13 tokens per session scan A 70c9bc4ca245

Subscribe to this mod's changes

skills is a command published in the GitHub repository SterlingChin/marvin-template (1,017 stars, last pushed 21d ago), licensed MIT. It adds 13 tokens to every session and 471 once invoked, about $0.0001 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 2026-08-30.