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/hongsw/plugin-for-claude-research/agentic-learningnpx skills add hongsw/plugin-for-claude-research --skill agentic-learninggit clone --depth 1 https://github.com/hongsw/plugin-for-claude-researchWrote 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/hongsw/plugin-for-claude-research/agentic-learning)<a href="https://agentmods.dev/skills/hongsw/plugin-for-claude-research/agentic-learning"><img src="https://agentmods.dev/badge/skills/hongsw/plugin-for-claude-research/agentic-learning.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 5.1 | $0.00070 | $0.01597 |
| Opus 5 | $0.00035 | $0.00798 |
| Sonnet 5 | $0.00014 | $0.00319 |
| Haiku 4.5 | $0.00007 | $0.00160 |
Grade A, and why
agentic-learning 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-Learning Skill — Claude Code 자기주도 학습
Core Purpose
사용자가 Claude Code의 핵심 기능을 스스로 학습할 수 있도록 돕는 인터랙티브 학습 프레임워크입니다. ai-native-camp/camp-1 커리큘럼을 기반으로 설계되었습니다.
통일 주제: PPTX 자동 생성 프로젝트
모든 레볼루션은 하나의 프로젝트를 공통 예시로 사용합니다.
목표: Claude Code로 PPTX를 자동으로 만드는 팀 시스템 구축
담당 역할 3가지:
🎨 테마 설정 담당 — 슬라이드 디자인, 색상, 폰트 결정
✍️ 내용 수정 담당 — 슬라이드 텍스트, 구조, 논리 흐름
🖨️ 렌더링 담당 — HTML → PPTX 변환, 파일 출력
각 레볼루션마다 이 프로젝트에 새로운 Claude Code 기능을 적용하며 점진적으로 완성합니다.
학습 방식: STOP 프로토콜
각 레볼루션은 반드시 2턴 구조를 따릅니다:
Phase A (1턴): 개념 설명 → 실습 지시 → STOP (퀴즈 없음, 질문 없음)
- 참조 문서의 EXPLAIN 섹션을 읽고 설명
- 참조 문서의 EXECUTE 섹션을 읽고 실습 안내 (PPTX 프로젝트 맥락 포함)
- 마무리: "👆 위 내용을 직접 실행해보세요. 실행이 끝나면 '완료' 또는 '다음'이라고 입력해주세요."
Phase B (2턴): 퀴즈 → 피드백 → 다음 레볼루션 안내
- 참조 문서의 QUIZ 섹션을 읽고 AskUserQuestion으로 퀴즈 출제
- 정답/오답 피드백 제공
- 다음 레볼루션으로 이동 여부 확인
절대 규칙
- Phase A에서 절대 AskUserQuestion을 호출하지 않는다
- Phase A에서 퀴즈 내용을 절대 노출하지 않는다
- "해보셨나요?" 같은 질문을 하지 않는다
- 각 레볼루션 시작 전 공식 문서 URL을 출력한다
- 개념 설명 후 반드시 PPTX 프로젝트에서의 활용 예시를 보여준다
학습 과정 (Learning Pipeline)
레볼루션 0: 환경 설정
Prompt: prompts/setup.md
Purpose: Claude Code 설치 및 초기 설정
PPTX 연결: PPTX 프로젝트 디렉토리 구조 만들기
Reference: references/rev0-setup.md
레볼루션 1: 체험 — 먼저 느껴보기
Prompt: prompts/experience.md
Purpose: Claude Code의 가능성을 3가지 데모로 체험
PPTX 연결: "PPTX 만들어줘" 한 마디로 슬라이드 생성 체험
Reference: references/rev1-experience.md
레볼루션 2: 왜 터미널인가?
Prompt: prompts/why-cli.md
Purpose: CLI 기반 Claude Code의 필요성 이해
PPTX 연결: PPTX 반복 생성 자동화 vs 수작업 비교
Reference: references/rev2-why.md
레볼루션 3: 7대 핵심 기능
Prompt: prompts/core-features.md
Purpose: Claude Code 7대 핵심 기능 학습
PPTX 연결: 각 기능을 PPTX 프로젝트에 직접 적용
References:
references/rev3-1-claude-md.md— CLAUDE.md → PPTX 스타일 가이드 정의references/rev3-2-skill.md— Skill → pptx-theme-setter 스킬 제작references/rev3-3-mcp.md— MCP → Playwright로 PPTX 렌더링references/rev3-4-subagent.md— Subagent → 테마/내용/렌더링 독립 작업references/rev3-5-agent-teams.md— Agent Teams → 3담당 협업 시스템references/rev3-6-hook.md— Hook → 저장 시 자동 품질 검사references/rev3-7-plugin.md— Plugin → PPTX 도구 패키지 배포
What ships with it
21 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.
- prompts/basics.md 2.0 KB
- prompts/core-features.md 5.1 KB
- prompts/create-skill.md 2.4 KB
- prompts/experience.md 1.7 KB
- prompts/research-integration.md 3.0 KB
- prompts/setup.md 1.6 KB
- prompts/why-cli.md 1.8 KB
- README.md 4.0 KB
- references/rev0-setup.md 2.4 KB
- references/rev1-experience.md 2.4 KB
- references/rev2-why.md 2.8 KB
- references/rev3-1-claude-md.md 2.3 KB
- references/rev3-2-skill.md 2.9 KB
- references/rev3-3-mcp.md 3.0 KB
- references/rev3-4-subagent.md 2.8 KB
- references/rev3-5-agent-teams.md 3.1 KB
- references/rev3-6-hook.md 3.3 KB
- references/rev3-7-plugin.md 3.1 KB
- references/rev4-basics.md 2.8 KB
- references/rev5-create-skill.md 3.7 KB
- references/rev6-research-integration.md 5.1 KB
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 · 139 lines · 70 tokens per session scan A 303b86c92c18
agentic-learning is a skill published in the GitHub repository hongsw/plugin-for-claude-research (20 stars, last pushed 4mo ago), licensed MIT. It adds 70 tokens to every session and 1,597 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 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).