new-skill

new-skill is a skill for Claude Code, Codex from shane9coy/Agent-Skill-Architecture-Guide. It costs 80 tokens per session (2,599 once invoked), scanned D, original, MIT.

A skill for creating, installing, checking, and repairing Codex skills in folders such as .codex/skills/ and .agents/skills/.

In plain words
What is it for?
Use it to scaffold a skill, add one from a URL, GitHub repository, ZIP file, or Markdown, and validate or troubleshoot an existing skill.
Why use it?
It provides a repeatable structure for skills and helps catch registration or configuration problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument; reads ~/.codex paths; mentions AGENTS.md.

Good fit Use it to scaffold a skill, add one from a URL, GitHub repository, ZIP file, or Markdown, and validate or troubleshoot an existing skill.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shane9coy/agent-skill-architecture-guide/new-skill-builder
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 shane9coy/Agent-Skill-Architecture-Guide --skill new-skill-builder
Clone the repo
git clone --depth 1 https://github.com/shane9coy/Agent-Skill-Architecture-Guide

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 new-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/shane9coy/agent-skill-architecture-guide/new-skill-builder/github.svg)](https://agentmods.dev/skills/shane9coy/agent-skill-architecture-guide/new-skill-builder)
Your own site
<a href="https://agentmods.dev/skills/shane9coy/agent-skill-architecture-guide/new-skill-builder"><img src="https://agentmods.dev/badge/skills/shane9coy/agent-skill-architecture-guide/new-skill-builder/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/skills/shane9coy/agent-skill-architecture-guide/new-skill-builder"><img src="https://agentmods.dev/badge/skills/shane9coy/agent-skill-architecture-guide/new-skill-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,599 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 $0.00080 $0.02599
Opus 5.5 $0.00032 $0.01040
Sonnet 5.5 $0.00016 $0.00520
Haiku 4.5 $0.00008 $0.00260

Measured 2mo ago against content hash 14f976187187, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

new-skill 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 2mo 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.

find .codex/skills .agents/skills skills -name "SKILL.md" 2>/dev/null || echo "No skills directory found"

Recursive force deletehighDestructive command

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

rm -rf "/tmp/${SKILL_NAME}-clone"
skills/new-skill-builder/SKILL.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New Skill Installer & Scaffolder

Overview

This skill helps you install, create, and manage skills in your Codex-first .codex/skills/ or .agents/skills/ directory. It handles the full lifecycle: scaffolding new skills from scratch, installing skills from external sources, validating skill structure, and troubleshooting registration issues.


Workflow 1: Create a New Skill From Scratch

When the user wants to create a brand new skill:

  1. Ask for details (if not provided):

    • Skill name (lowercase, hyphenated, e.g. api-tester)
    • What it should do (purpose)
    • When it should trigger (contexts)
    • Whether it needs scripts, references, or assets
  2. Scaffold the folder structure:

SKILL_NAME="the-skill-name"
PROJECT_DIR="$(pwd)"
SKILL_DIR="${PROJECT_DIR}/.codex/skills/${SKILL_NAME}"

mkdir -p "${SKILL_DIR}"
mkdir -p "${SKILL_DIR}/scripts"
mkdir -p "${SKILL_DIR}/references"
mkdir -p "${SKILL_DIR}/assets"
  1. Generate the SKILL.md with proper frontmatter:
---
name: {skill-name}
description: "{What it does}. Use when {trigger conditions}. Handles {capabilities}."
---

# {Skill Title}

## Overview
{One paragraph purpose statement}

## Instructions
1. {Step-by-step instructions}

## Examples
### Example 1
**Input:** "{example user request}"
**Action:** {what the skill does}
**Output:** {expected result}

## Error Handling
- {How to handle failures}

## Notes
- {Caveats and edge cases}
  1. Validate the skill (run Workflow 4 below)

  2. Report back with the file tree and confirmation it's registered.


Workflow 2: Install a Skill From External Source

When the user provides a URL, GitHub repo, zip file, or raw markdown:

From a GitHub Repository URL

REPO_URL="$1"
SKILL_NAME="$2"  # Extract from repo name if not given
SKILL_DIR=".codex/skills/${SKILL_NAME}"

# Clone just the skill content
git clone --depth 1 "${REPO_URL}" "/tmp/${SKILL_NAME}-clone"

# Find the SKILL.md
SKILL_FILE=$(find "/tmp/${SKILL_NAME}-clone" -name "SKILL.md" -type f | head -1)

if [ -z "$SKILL_FILE" ]; then
  echo "ERROR: No SKILL.md found in repository."
  echo "This repo may not be a valid AgentSkills package."
  exit 1
fi

# Get the skill's parent directory (contains SKILL.md + siblings)
SKILL_SRC=$(dirname "$SKILL_FILE")

# Copy to .codex/skills/
mkdir -p "${SKILL_DIR}"
cp -r "${SKILL_SRC}/"* "${SKILL_DIR}/"

# Cleanup
rm -rf "/tmp/${SKILL_NAME}-clone"

echo "Installed ${SKILL_NAME} to ${SKILL_DIR}"

Read the full file on GitHub · 322 lines

Files

What ships with it

4 files 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. 2mo ago First seen · 322 lines · 80 tokens per session scan D 14f976187187

Subscribe to this mod's changes

new-skill is a skill published in the GitHub repository shane9coy/Agent-Skill-Architecture-Guide (20 stars, last pushed 5mo ago), licensed MIT. It adds 80 tokens to every session and 2,599 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it D with 2 findings (enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

new-skill compared with skills from other repositories

new-skill next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
new-skillshane9coy/Agent-Skill-Architecture-GuideSkill205mo agoMITD80Claude Code, Codex
exploratory-data-analysisK-Dense-AI/scientific-agent-skillsSkill57k4d agoMITA83Claude Code
webhook-managementhoangsonww/Claude-Code-Agent-MonitorSkill1.2ktodayMITA56Claude Code, Codex
gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-rechtSkill1.8ktodayApache-2.0A69Claude Code
accessibility-patternsvibeeval/vibecosystemSkill547yesterdayMITA24Claude Code, Codex
render-3d-product-showcasegooseworks-ai/goose-skillsSkill1.3k6d agoMITA159Claude Code, Codex
render-airdrop-carouselgooseworks-ai/goose-skillsSkill1.3k6d agoMITA207Claude Code, Codex