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 skills/imgompanda/fireauto/fireauto-self-learn-guidenpx skills add imgompanda/fireauto --skill fireauto-self-learn-guidegit clone --depth 1 https://github.com/imgompanda/fireautoWrote 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/skills/imgompanda/fireauto/fireauto-self-learn-guide)<a href="https://agentmods.dev/skills/imgompanda/fireauto/fireauto-self-learn-guide"><img src="https://agentmods.dev/badge/skills/imgompanda/fireauto/fireauto-self-learn-guide.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 | $0.00085 | $0.00629 |
| Opus 5 | $0.00043 | $0.00315 |
| Sonnet 5 | $0.00017 | $0.00126 |
| Haiku 4.5 | $0.00009 | $0.00063 |
Grade A, and why
fireauto-self-learn-guide 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 3d 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
자기학습 가이드
언제 트리거되나요?
다음 상황에서 이 가이드를 참고하세요:
- 실수 감지: 사용자가 "아니", "잘못", "틀렸", "그게 아니라", "다시 해"를 말할 때
- 수정 요청: 사용자가 코드 수정을 요청할 때
- 패턴 반복: 같은 작업이 3회 이상 반복될 때
실수 감지 (자동)
사용자가 수정을 요청하면 즉시 실행하세요:
Step 1: 실수 기록
mistake-log MCP 도구로 기록하세요:
- 뭘 잘못했는지
- 왜 잘못했는지
- 어떻게 고쳤는지
Step 2: Wiki 업데이트
wiki-write MCP 도구로 gotchas.md를 업데이트하세요.
Step 3: CLAUDE.md 규칙 추가
같은 실수 방지 규칙을 CLAUDE.md에 추가하세요.
Step 4: 사용자에게 알림
⚠️ 실수 기록: {내용}. 다음부터 주의할게요.
패턴 감지 (자동)
같은 작업이 3회 이상 반복되면 실행하세요:
Step 1: 패턴 추출
반복되는 작업에서 공통 패턴을 추출하세요.
Step 2: 스킬 저장
skill-save MCP 도구로 DB에 저장하세요.
Step 3: 스킬 파일 생성
.claude/skills/에 스킬 파일을 생성하세요.
Step 4: Wiki 업데이트
wiki-write MCP 도구로 skills-catalog.md를 업데이트하세요.
🔧 새 스킬 생성: {스킬명}
{스킬 설명}
반복 횟수 {N}회에서 자동 감지됐어요.
CLAUDE.md 관리
- 실수 기반 규칙 → 즉시 CLAUDE.md에 추가
- 80줄 초과 시 오래된 규칙을 Wiki로 이동
- "이 줄을 제거하면 Claude가 실수할까?" — 아니면 삭제
톤 & 스타일
- 문체: 토스체 — 친근하고 간결하게
- 분량: 핵심만 짧게. 장황하게 설명하지 않아요
- 행동 유도: 실수 기록 후 개선 방향을 제안해요
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.
- 3d ago First seen · 92 lines · 85 tokens per session scan A 3c5a2455d003
fireauto-self-learn-guide is a skill published in the GitHub repository imgompanda/fireauto (140 stars, last pushed 4mo ago), licensed MIT. It adds 85 tokens to every session and 629 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
anyui-template-authoring
Author and invoke high-quality, mobile-first AnyUI HTML templates for MioChat. Guides the creation of clean, responsive cards, game interfaces, forms, story choices, and Galgame/visual novel dialogue cards rendered via extraRender in Shadow DOM. Enforces decoupled zero-round-trip async image rendering (pure CSS…
ui5-best-practices-accessibility
This skill should be used when the user asks to audit, fix, check, review, or improve accessibility, a11y, ARIA, WCAG compliance, landmarks, labeling, heading levels, focus handling, keyboard navigation, keyboard shortcuts, screen reader support, invisible messaging, reading order, or touch / target size in UI5…
tw-easing-gradients
Replace Tailwind CSS linear gradients with smooth eased gradients using tw-easing-gradients. Use when upgrading bg-gradient-to-, creating fading backgrounds, or smooth color transitions.
tanstack-ranger
Headless utilities for building range and multi-range sliders in TS/JS, React, Vue, Solid, Svelte & Angular.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.