aget-create-skill

aget-create-skill is a skill for Claude Code from aget-framework/template-advisor-aget. It costs 37 tokens per session (1,161 once invoked), scanned B, a copy of aget-create-skill, Apache-2.0.

A guided process for creating AGET skills, which are reusable instructions for an agent. It checks names, templates, numbering, and project records before creating a skill.

In plain words
What is it for?
Use it to start a new skill interactively or from a supplied name, validate the S-V-O naming pattern, check for conflicts, and register the skill correctly.
Why use it?
It prevents new skills from using inconsistent names or conflicting with existing skills. It also keeps their specifications and history traceable.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it to start a new skill interactively or from a supplied name, validate the S-V-O naming pattern, check for conflicts, and register the skill correctly.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aget-framework/template-advisor-aget/aget-create-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.

Any agent
npx skills add aget-framework/template-advisor-aget --skill aget-create-skill
Clone the repo
git clone --depth 1 https://github.com/aget-framework/template-advisor-aget

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 aget-create-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-create-skill.svg)](https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-create-skill)
Your own site
<a href="https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-create-skill"><img src="https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-create-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,161 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 97% copy Near-identical to another mod 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 $0.00037 $0.01161
Opus 5 $0.00018 $0.00580
Sonnet 5 $0.00007 $0.00232
Haiku 4.5 $0.00004 $0.00116

Measured 7d ago against content hash d7a2d8976f52, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

aget-create-skill 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 7d 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls .claude/skills/ | grep -q "<name>"
Origin

This is a copy

97% identical to aget-create-skill — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/aget-create-skill/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aget-create-skill

Create a new AGET skill following the standard development process per SOP_SKILL_DEVELOPMENT.md.

Input

$ARGUMENTS

Mode Detection

Input Pattern Mode Behavior
Empty or blank Interactive Prompt for skill name
<skill-name> Explicit Create skill with provided name

Skill Creation Process

Step 1: Name Validation

Validate the skill name follows S-V-O convention:

Pattern Valid Examples
/aget-<verb>-<object> ✓ Default /aget-create-skill, /aget-check-health
/aget-<verb> ✓ Intransitive /aget-learn, /aget-checkpoint
/aget-<phrasal-verb> ✓ Exception /aget-wake-up, /aget-wind-down
Other patterns ✗ Invalid /aget-skill-create (O-V not S-V-O)

Check for existing skill:

ls .claude/skills/ | grep -q "<name>"

If skill exists, STOP and report conflict.

Step 2: Determine Skill Number

Check specs/skills/INDEX.md for next available SKILL-XXX number.

Current registry:

  • SKILL-001 through SKILL-005: Existing
  • SKILL-006: Reserved for /aget-create-project
  • SKILL-007: This skill (/aget-create-skill)
  • SKILL-008+: Available

Step 3: Create Skill Specification

Create specs/skills/SKILL-XXX_<name>.md with:

  1. Purpose section
  2. Requirements (R-SKILL-XXX-001, etc.) in EARS format
  3. Test cases
  4. Traceability section

Step 4: Create SKILL.md

  1. Create directory: .claude/skills/<name>/
  2. Copy structure from templates/skill/SKILL.template.md
  3. Fill in required fields:

Required frontmatter:

---
name: <name>
description: <one-line description>
---

For skills with side effects (file writes, git operations):

disable-model-invocation: true

Instruction format (per L561 - Instruction Asymmetry):

  • Use PROHIBITIVE form: "NEVER", "SHALL NOT", "DO NOT"
  • Avoid affirmative form (~0% compliance)

Step 5: Update Index

Add entry to specs/skills/INDEX.md:

Read the full file on GitHub · 149 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. 7d ago First seen · 149 lines · 37 tokens per session scan B d7a2d8976f52

Subscribe to this mod's changes

aget-create-skill is a skill published in the GitHub repository aget-framework/template-advisor-aget (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,161 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). It is 97% identical to aget-create-skill, differing in 2 lines, and is treated as a copy.