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.
npx agentmods add instructions/gmickel/better-skill-builder/claude-mdgit clone --depth 1 https://github.com/gmickel/better-skill-builderWrote 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.
[](https://agentmods.dev/instructions/gmickel/better-skill-builder/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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:
- Keep SKILL.md under 500 lines (progressive disclosure)
- Put detailed examples in references/
- Update real-examples.md when skills change
- Keep README.md in sync with SKILL.md highlights
Official Docs
The canonical Agent Skills spec lives at:
- https://agentskills.io/specification
- https://agentskills.io/integrate-skills
- https://agentskills.io/home
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
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.
- 5d ago First seen · 51 lines · 356 tokens per session scan A 1df4ad978340
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.
Other instructions, from other repositories
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
superpowers-reasonix AGENTS.md
Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.
ai-mind AGENTS.md
AGENTS.md instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.
vvvv-skills CLAUDE.md
Claude Code instructions for tebjan/vvvv-skills, covering vvvv gamma, when to patch vs code, core concepts, live environment and important conventions.
pi AGENTS.md
AGENTS.md instructions for counterposition/pi, covering agents.md, commands, pattern: pnpm --filter @counterposition/pi-web-search run, single test file and single test by name.
SciCrucible CLAUDE.md
Claude Code instructions for Xinyang-Li666/SciCrucible, covering 科学知识库, 知识库结构, 可用命令, 项目目录 and 工作原则.