agent-skills: Skill for Claude Code

.claude/skills/simple-skills-manager/SKILL.md

simple-skills-manager is a skill for Claude Code from ArcBlock/agent-skills. It costs 34 tokens per session (3,687 once invoked), scanned D, original, MIT.

A manager for skills stored locally or in Git repositories. It adds, updates, or removes shortcut entries in the Claude skills directory so those skills can be invoked by name.

In plain words
What is it for?
Use it to add skills from a local path or Git URL, refresh an existing skill group, or remove one from the managed skills directory.
Why use it?
It avoids manually copying or maintaining skill references when skills come from different locations.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

This is ArcBlock/agent-skills's own configuration. It tells Claude Code how to work on agent-skills 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 agent-skills configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/user/projects/my-plugin.

Reuse

Borrowing it

Nothing to install: this file belongs to ArcBlock/agent-skills. 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/ArcBlock/agent-skills/main/.claude/skills/simple-skills-manager/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ArcBlock/agent-skills

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 simple-skills-manager

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/arcblock/agent-skills/simple-skills-manager"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/simple-skills-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,687 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 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 $0.00034 $0.03687
Opus 5 $0.00017 $0.01843
Sonnet 5 $0.00007 $0.00737
Haiku 4.5 $0.00003 $0.00369

Measured 9d ago against content hash 47d674f84904, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade D, and why

simple-skills-manager scanned grade D with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/simple-skills-manager-repos/{group}/path.txt

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.claude/simple-skills-manager-backup-last-skills
.claude/skills/simple-skills-manager/SKILL.md · 372 lines

How it starts

The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Simple Skills Manager

Manage skill tips in ~/.claude/skills/ that point to skills from local paths or git repositories, enabling dynamic invocation via /{group}-{skill-name}.

Note: We use hyphen - as separator instead of colon : because Windows paths don't support colons in filenames.

Constants

  • Repos directory: ~/.claude/simple-skills-manager-repos/
  • Skills directory: ~/.claude/skills/
  • Backup directory: ~/.claude/simple-skills-manager-backup-last-skills/

Workflow

Step 1: Ask Operation Type

First, ask the user what operation they want to perform:

{
  "questions": [{
    "question": "What operation would you like to perform?",
    "header": "Operation",
    "options": [
      {"label": "Add (Recommended)", "description": "Add skills from a local path or git repository"},
      {"label": "Update", "description": "Update an existing skill group (re-sync from source)"},
      {"label": "Remove", "description": "Remove an existing skill group"}
    ],
    "multiSelect": false
  }]
}

Step 2: Collect Information Based on Operation

For "Add" Operation

Ask user to directly input the source path or git URL:

{
  "questions": [{
    "question": "Please enter the local path or git URL for the skills:",
    "header": "Source",
    "options": [
      {"label": "Example: /path/to/skills", "description": "Local directory containing SKILL.md files"},
      {"label": "Example: https://github.com/user/repo.git", "description": "Git repository URL (will be cloned)"}
    ],
    "multiSelect": false
  }]
}

The user will select "Other" and type the actual path or URL. The system will auto-detect the source type:

  • Git URL: starts with http://, https://, git@, or ends with .git
  • Local path: everything else (treat as filesystem path)

After getting the source, ask for the group name:

{
  "questions": [{
    "question": "What group name should be used as prefix? (e.g., 'mygroup' creates '/mygroup-skill-name')",
    "header": "Group",
    "options": [
      {"label": "Use folder name", "description": "Use the source folder/repo name as group"},
      {"label": "Custom", "description": "Enter a custom group name"}
    ],
    "multiSelect": false
  }]
}

Read the full file on GitHub · 372 lines

Files

What ships with it

1 file 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 · 372 lines · 34 tokens per session scan D 47d674f84904

Subscribe to this mod's changes

simple-skills-manager is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 3,687 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens