new-skill

new-skill is a command for Claude Code from davistroy/claude-marketplace. It costs 14 tokens per session (4,407 once invoked), scanned A, original, MIT.

A command that creates a new skill file with the folder structure and frontmatter needed for Claude Code to find it. Frontmatter is the metadata at the top of the file.

In plain words
What is it for?
Use it when adding a skill to a plugin. It accepts a kebab-case skill name, can target a plugin, and can base the file on a chosen pattern.
Why use it?
It prevents skills and commands from being laid out or labelled incorrectly. It can also apply a selected starting pattern, such as planning or workflow.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Part of the personal-plugin plugin — 29 skills, 23 commands, 10 agents, 2 hooks shipped together

Good fit Use it when adding a skill to a plugin. It accepts a kebab-case skill name, can target a plugin, and can base the file on a chosen pattern.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/davistroy/claude-marketplace/new-skill
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.

Clone the repo
git clone --depth 1 https://github.com/davistroy/claude-marketplace

Made for: Claude Code.

Or install personal-plugin, the plugin that ships this one along with the rest of its 29 skills, 23 commands, 10 agents, 2 hooks.

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 new-skill

README.md
[![agentmods](https://agentmods.dev/badge/commands/davistroy/claude-marketplace/new-skill/github.svg)](https://agentmods.dev/commands/davistroy/claude-marketplace/new-skill)
Your own site
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/new-skill"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/new-skill/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 new-skill

Your own site · 80×15
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/new-skill"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/new-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,407 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 $0.00014 $0.04407
Opus 5 $0.00007 $0.02204
Sonnet 5 $0.00003 $0.00881
Haiku 4.5 $0.00001 $0.00441

Measured 11d ago against content hash 098c84c9321b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

new-skill 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 11d 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.

plugins/personal-plugin/commands/new-skill.md · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New Skill Generator

Generate a new skill for this plugin with the correct directory structure and frontmatter. This command ensures skills are discoverable by Claude Code by using the required nested directory pattern.

CRITICAL: Skills have DIFFERENT requirements than commands:

  • Skills use nested directories: skills/[name]/SKILL.md
  • Skills REQUIRE a name field in frontmatter
  • Commands use flat files and FORBID the name field

Input Validation

Optional Arguments:

  • <skill-name> - Name for the new skill (kebab-case)
  • --plugin <plugin-name> - Target plugin (defaults to auto-detected or prompted)
  • --pattern <name> - Base the skill on a command-pattern template instead of the default skill template (see Phase 2.2 "Pattern Adaptation"). One of conversion, generator, interactive, planning, read-only, synthesis, utility, workflow — see references/skill-patterns.md for a one-line description of each. Omit for today's default behavior (generates from references/templates/skill.md).

Plugin Target Resolution:

  1. If --plugin is specified, use that plugin
  2. If the current working directory is inside a plugin, use that plugin
  3. If only one plugin exists in plugins/, use it automatically
  4. If multiple plugins exist, scan plugins/*/ using the Glob tool and prompt the user:
    Multiple plugins detected:
      [1] personal-plugin
      [2] bpmn-plugin
    
    Which plugin should this skill be added to? (1/2):
    

Validation: If arguments are missing, the command will prompt interactively.

Skill name must be:

  • kebab-case format (e.g., my-new-skill)
  • Unique (not already exist in the target plugin's skills/ directory)
  • Descriptive but concise

Pattern Validation: If --pattern <name> is given and <name> is not one of the 8 listed above, display:

Error: Unknown pattern '[name]'

Valid patterns: conversion, generator, interactive, planning, read-only, synthesis, utility, workflow

Omit --pattern to use the default skill template.

Read the full file on GitHub · 390 lines

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. 11d ago First seen · 390 lines · 14 tokens per session scan A 098c84c9321b

Subscribe to this mod's changes

new-skill is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 4,407 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 2026-08-31.