skill-installer

skill-installer is a skill for Claude Code, Codex from donggua-zen/guada. It costs 48 tokens per session (1,552 once invoked), scanned A, original, MIT.

A skill manager for installing, updating, and removing AI skills from Git repositories, ZIP files, or manually created folders.

In plain words
What is it for?
Use it when someone asks to install, download, add, import, set up, update, or uninstall a skill.
Why use it?
It gives installation a consistent process and checks a skill before placing it in the system skills directory.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when someone asks to install, download, add, import, set up, update, or uninstall a skill.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/donggua-zen/guada/skill-installer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add donggua-zen/guada --skill skill-installer
Clone the repo
git clone --depth 1 https://github.com/donggua-zen/guada

Made for: Claude Code, Codex.

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 skill-installer

README.md
[![agentmods](https://agentmods.dev/badge/skills/donggua-zen/guada/skill-installer.svg)](https://agentmods.dev/skills/donggua-zen/guada/skill-installer)
Your own site
<a href="https://agentmods.dev/skills/donggua-zen/guada/skill-installer"><img src="https://agentmods.dev/badge/skills/donggua-zen/guada/skill-installer.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,552 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 39
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium Rogue Agent · line 39
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00048 $0.01552
Opus 5 $0.00024 $0.00776
Sonnet 5 $0.00010 $0.00310
Haiku 4.5 $0.00005 $0.00155

Measured 8d ago against content hash 29f386e7b350, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

skill-installer 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate-skill.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

backend-ts/bundled-skills/skill-installer/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Installer — Skill Installation & Management Guide

Overview

This skill guides you through installing, updating, and uninstalling skills. The core workflow is:

Download/Prepare → Validate (must pass) → Install to ~/.guada/skills/<name>/

Target directory: ~/.guada/skills/ (Windows: C:\Users\<username>\.guada\skills\)


1. Installation Workflow

All installation methods follow the same three-step workflow.

1.1 Download — to Working Directory

Place the skill source in the current working directory, not the target directory:

# Git clone
git clone https://github.com/.../repo.git  ./<skill-name>

# ZIP extraction
unzip skill.zip -d ./<skill-name>

# Manual creation
mkdir ./<skill-name>  (then edit SKILL.md)

1.2 Validate — Must Pass

Run the bundled validation script before installing:

node ~/.guada/skills/skill-installer/scripts/validate-skill.mjs ./<skill-name>

All 14 checks must pass before proceeding. If validation fails, fix the reported issues and re-run until it passes.

1.3 Install — Move to System Directory

Once validated, move the directory to the target location:

mv ./<skill-name> ~/.guada/skills/<skill-name>

The file watcher automatically detects and registers the skill within seconds.


2. Installation Methods

2.1 From Git Repository

Best for: Published skills, team-shared skills, version history.

Required from user:

  • Git URL (required): e.g. https://github.com/owner/repo or [email protected]:owner/repo.git
  • Branch (optional): specific branch (defaults to repo default)
  • Subdirectory (optional): path in monorepos where the skill lives

Steps:

  1. Validate Git URL format (must start with http://, https://, or git@)
  2. Clone to current working directory: git clone --depth 1 <url> ./temp-<name>
  3. Locate SKILL.md (search root, then 1-2 levels deep)
  4. Extract name from frontmatter
  5. Run validation script (must pass)
  6. Check for naming conflicts in target directory
  7. Move to ~/.guada/skills/<name>/
  8. Clean up temp files
  9. File watcher auto-detects and registers

Read the full file on GitHub · 182 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. 8d ago First seen · 182 lines · 48 tokens per session scan A 29f386e7b350

Subscribe to this mod's changes

skill-installer is a skill published in the GitHub repository donggua-zen/guada (57 stars, last pushed 25d ago), licensed MIT. It adds 48 tokens to every session and 1,552 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

compose-agents-md

Meta-skill: helps create an AGENTS.md for a new project by guiding the user through selecting the right profile from the agentic library and running the compose command. Also helps create a custom AGENTS.md from scratch when no profile fits. Invoked when the user asks to set up agent instructions, create AGENTS.md, or…

soulcodex/agentic · 78 tokens

shadcn/ui expert

Use shadcn/ui as a composable, copy-owned component baseline. Customise design tokens to match the product; never treat the library as a locked black box.

LuuOW/meridian-mcp · 33 tokens

mpm-init

Initialize or update project for Claude Code and MPM.

bobmatnyc/claude-mpm · 14 tokens

skill-creator

Propose, test, validate, and improve Skill candidates without changing active files - generate reviewable SKILL.md and handler.js drafts, run test evaluations, and optimize descriptions for better triggering.

chainlesschain/chainlesschain · 41 tokens

torchforge-rl-training

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

davila7/claude-code-templates · 49 tokens

scaffold

Use when starting hyperflow in a new project, refreshing the .hyperflow/ cache, or installing auto-detection shims (AGENTS.md, CLAUDE.md). One-shot project setup; does not start the spec → scope → dispatch chain. Trigger with /hyperflow:scaffold, "init hyperflow", "set up hyperflow", "refresh hyperflow", "install…

jeremylongshore/tons-of-skills-marketplace · 86 tokens