better-skill-builder CLAUDE.md

better-skill-builder CLAUDE.md is an instructions file for coding agents from gmickel/better-skill-builder. It costs 356 tokens per session, scanned A, original, MIT.

A guide for creating Agent Skills, which are instruction packages that teach AI assistants how to handle a particular kind of work. It defines the repository layout, documentation limits, update rules, and links to the official specification.

In plain words
What is it for?
Use it when writing or updating a skill, its reference documents, examples, README, or plugin-format guidance.
Why use it?
It helps keep skill instructions organized, short enough to load, and consistent with the documented format.

Instructions file

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.

agentmods
npx agentmods add instructions/gmickel/better-skill-builder/claude-md
Clone the repo
git clone --depth 1 https://github.com/gmickel/better-skill-builder

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 better-skill-builder CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gmickel/better-skill-builder/claude-md.svg)](https://agentmods.dev/instructions/gmickel/better-skill-builder/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/gmickel/better-skill-builder/claude-md"><img src="https://agentmods.dev/badge/instructions/gmickel/better-skill-builder/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 356 This file is loaded in full into every session.
When invoked 356 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00356 $0.00356
Opus 5 $0.00178 $0.00178
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00036 $0.00036

Measured 5d ago against content hash 1df4ad978340, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

better-skill-builder CLAUDE.md 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 5d 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.

CLAUDE.md · 51 lines

What it actually says

gmickel-skill

Guide for building Agent Skills. This repo is itself a skill.

Structure

SKILL.md                      # Main skill (loaded by AI assistants)
README.md                     # GitHub landing page
references/
  patterns.md                 # Detailed patterns
  plugin-structure.md         # Plugin/marketplace format
  real-examples.md            # Production examples

Updating

When updating skill content:

  1. Keep SKILL.md under 500 lines (progressive disclosure)
  2. Put detailed examples in references/
  3. Update real-examples.md when skills change
  4. Keep README.md in sync with SKILL.md highlights

Official Docs

The canonical Agent Skills spec lives at:

If user asks about spec details not covered here, fetch from those URLs.

Skills Referenced

This repo documents these skills (keep descriptions current):

Skill Repo Pattern
gno github.com/gmickel/gno CLI with skill management
sheets-cli github.com/gmickel/sheets-cli CLI with install-skill
raindrop-skill github.com/gmickel/raindrop-skill Helper script + git clone
outlookctl github.com/gmickel/outlookctl Safety-first, nested skill
flow github.com/gmickel/gmickel-claude-marketplace Plugin bundle

Style

  • Concise, no fluff
  • No em-dashes
  • Code examples over prose
  • Tables for quick reference
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. 5d ago First seen · 51 lines · 356 tokens per session scan A 1df4ad978340

Subscribe to this mod's changes

better-skill-builder CLAUDE.md is an instructions file published in the GitHub repository gmickel/better-skill-builder (8 stars, last pushed 8mo ago), licensed MIT. It adds 356 tokens to every session, about $0.0018 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.