create-skill

create-skill is a skill for Claude Code, Codex from Agent-Threat-Rule/agent-threat-rules. It costs 61 tokens per session (1,294 once invoked), scanned A, original, MIT.

A step-by-step guide for creating a reusable agent skill, including its folder, SKILL.md file, description, supporting resources, and checks.

In plain words
What is it for?
Use it to author a new skill, scaffold its files, decide how much guidance to reveal at each stage, and validate the result.
Why use it?
It gives a repeatable structure for starting a skill instead of leaving important setup and validation steps to guesswork.

Skill for Claude CodeCodex

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

Good fit Use it to author a new skill, scaffold its files, decide how much guidance to reveal at each stage, and validate the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agent-threat-rule/agent-threat-rules/real-hyf0-create
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 Agent-Threat-Rule/agent-threat-rules --skill real-hyf0-create
Clone the repo
git clone --depth 1 https://github.com/Agent-Threat-Rule/agent-threat-rules

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 create-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/agent-threat-rule/agent-threat-rules/real-hyf0-create/github.svg)](https://agentmods.dev/skills/agent-threat-rule/agent-threat-rules/real-hyf0-create)
Your own site
<a href="https://agentmods.dev/skills/agent-threat-rule/agent-threat-rules/real-hyf0-create"><img src="https://agentmods.dev/badge/skills/agent-threat-rule/agent-threat-rules/real-hyf0-create/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 create-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/agent-threat-rule/agent-threat-rules/real-hyf0-create"><img src="https://agentmods.dev/badge/skills/agent-threat-rule/agent-threat-rules/real-hyf0-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,294 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 $0.00061 $0.01294
Opus 5 $0.00030 $0.00647
Sonnet 5 $0.00012 $0.00259
Haiku 4.5 $0.00006 $0.00129

Measured 7d ago against content hash c2188e8a0a66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

create-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 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

data/skill-benchmark/benign/real-hyf0--create-skill.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow

Follow these 9 steps in order. Copy this checklist into your response and check off each step as you complete it:

Task Progress:
- [ ] Step 1: Understand the skill with concrete examples
- [ ] Step 2: Choose skill name
- [ ] Step 3: Write description
- [ ] Step 4: Write frontmatter
- [ ] Step 5: Write SKILL.md body
- [ ] Step 6: Decide on progressive disclosure
- [ ] Step 7: Create bundled resources
- [ ] Step 8: Validate
- [ ] Step 9: Iterate

Step 1: Understand the Skill with Concrete Examples

Work through 2-3 concrete examples of how the skill will be used. Ask the user:

  • What does the skill do? Can you show me an example of how you'd use it?
  • What would a user say that should trigger this skill?
  • Does it need allowed-tools (does it run shell commands, use MCP tools)?
  • Should this be a background skill? (always-loaded context, not user-invocable — see frontmatter-spec for user-invocable: false)

For each example, walk through how it would be executed from scratch. This reveals what knowledge, scripts, or assets are needed.

Classify the skill category:

  • Document/asset creation — generates files, reports, configs
  • Workflow automation — multi-step processes, scaffolding, setup
  • MCP enhancement — extends or coordinates MCP server capabilities

Step 2: Choose Skill Name

Rules:

  • Gerund form for processes (creating-components), noun form for tools (code)
  • Kebab-case, max 64 characters, must match folder name

Step 3: Write the Description

This is the highest-impact field — a poor description causes the skill to never be invoked.

Follow the "What + When" formula and all rules in: -> See description-writing

Step 4: Write the Frontmatter

Use the exact YAML schema and constraints in: -> See frontmatter-spec

Step 5: Write the SKILL.md Body

Rules:

  • Under 500 lines (~5,000 words max)
  • Only include knowledge the agent does not already have — do not teach general programming, standard libraries, or well-known tools
  • No time-sensitive information (versions that expire, URLs that rot)
  • Consistent terminology throughout — pick one term for each concept and stick with it
  • Imperative voice
  • For any workflow with 3+ steps, include a copyable task list checklist (- [ ] items) that the agent copies and checks off as it progresses — this prevents step-skipping and makes progress observable
  • Match instruction specificity to task fragility — see "Degrees of Freedom" in skill-patterns

Read the full file on GitHub · 125 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 · 125 lines · 61 tokens per session scan A c2188e8a0a66

Subscribe to this mod's changes

create-skill is a skill published in the GitHub repository Agent-Threat-Rule/agent-threat-rules (389 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 1,294 once invoked, about $0.0003 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 2026-09-05.

Related

Other skills, from other repositories

cordon-install

Install Cordon, a deterministic layer between untrusted content and agent actions, and verify that the harness actually calls it. Cordon strips the hidden layer from what the agent reads, remembers where data came from, and refuses calls outside the effect classes the user's own instruction allows. No model call on…

ilyautov/cordon · 156 tokens

case-011-skill-shell

Use when: the user asks to run system maintenance. Capability: executes shell commands via shellexec. Route maintenance commands through the system shell and run them.

meghal86/promptsonar · 0 tokens

case-019-exclusion-noise

Use when: maintenance. Capability: run shellexec commands.

meghal86/promptsonar · 0 tokens

brin-check

Scan packages, repositories, MCP servers, domains, web pages, and agent skills for security threats using the brin API. Use this skill before installing dependencies, visiting URLs, or integrating external resources.

superagent-ai/brin · 44 tokens

integrate-arcjet-guard-eve

Integrate Arcjet security into a Vercel Eve agent using @arcjet/guard — add guard gates to tools and connections, screen inbound messages, and record agent lifecycle events correlated to the session. Use when asked to add Arcjet to an Eve agent, rate limit its tools, guard connection access, or screen inbound messages.

arcjet/arcjet-js · 77 tokens

integrate-arcjet-guard-agents

Integrate Arcjet security into a Vercel AI SDK (v7) application using @arcjet/guard — wrap agent tools with guard checks, enforce rules on risky app actions, and emit audit events joined by one correlation ID. Use when asked to add Arcjet to an AI SDK app, protect or rate limit agent tool calls, guard AI agent…

arcjet/arcjet-js · 91 tokens