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/hyperaiteam/clitrigger/lessonnpx skills add HyperAITeam/CLITrigger --skill lessongit clone --depth 1 https://github.com/HyperAITeam/CLITriggerWhat 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 | $0.00034 | $0.00768 |
| Opus 5 | $0.00017 | $0.00384 |
| Sonnet 5 | $0.00007 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
lesson 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 2d 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
교훈 캡처
목적
작업 중 발견한 실수, 주의사항, 유용한 패턴을 .claude/lessons.md에 기록하여 다음 세션에서 반복을 방지합니다.
카테고리
| 카테고리 | 키워드 | 용도 |
|---|---|---|
| 실수 (Mistakes) | 실수, mistake, 금지, 하지마 |
반복하면 안 되는 실수 |
| 주의 (Cautions) | 주의, caution, 조심, 확인 |
작업 시 주의할 점 |
| 패턴 (Patterns) | 패턴, pattern, 순서, 방법 |
따라야 할 올바른 패턴 |
워크플로우
Step 1: 인수 파싱
사용자 인수를 분석합니다:
카테고리: 내용형식이면 카테고리를 직접 사용- 카테고리 없이 내용만 있으면 키워드 기반으로 자동 판별:
- "~하지 마", "금지", "실수" → 실수
- "조심", "확인", "주의" → 주의
- "순서", "방법", "패턴", "~할 때" → 패턴
- 판별이 모호하면
AskUserQuestion으로 질문
인수가 비어있으면 AskUserQuestion으로 교훈 내용을 질문합니다.
Step 2: 중복 확인
.claude/lessons.md를 읽고 비슷한 교훈이 이미 있는지 확인합니다.
- 핵심 키워드가 70% 이상 겹치는 항목이 있으면 사용자에게 알림
- 기존 항목을 업데이트할지 새로 추가할지
AskUserQuestion으로 질문
Step 3: 교훈 추가
.claude/lessons.md의 해당 카테고리 섹션에 추가합니다:
형식:
- [YYYY-MM-DD] 교훈 내용
규칙:
- 오늘 날짜를 자동으로 삽입
- 한 줄로 간결하게 작성 (필요하면
—뒤에 이유 추가) - 해당 카테고리의 마지막 항목 뒤에 추가
Step 4: 확인
추가된 교훈을 사용자에게 보여줍니다:
교훈이 추가되었습니다:
- 카테고리: {카테고리}
- 내용: {내용}
- 파일: .claude/lessons.md
다음 세션부터 자동으로 컨텍스트에 포함됩니다.
서브커맨드
/lesson list
현재 등록된 모든 교훈을 카테고리별로 보여줍니다.
/lesson clean
오래된(90일+) 교훈이나 중복 항목을 찾아 정리를 제안합니다.
AskUserQuestion으로 각 항목의 삭제 여부를 확인합니다.
Related Files
| File | Purpose |
|---|---|
.claude/lessons.md |
교훈 저장 파일 |
.claude/hooks/load-recent-changes.sh |
SessionStart 훅 (lessons.md를 컨텍스트에 로드) |
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.
- 2d ago First seen · 87 lines · 34 tokens per session scan A c15a5b968c93
lesson is a skill published in the GitHub repository HyperAITeam/CLITrigger (13 stars, last pushed 8d ago), licensed MIT. It adds 34 tokens to every session and 768 once invoked, about $0.0002 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
design-retrospective
Analyze design session feedback, extract aesthetic lessons into .design-system/lessons-learned.md, promote recurring patterns to design-principles.md, write taste-profile and cross-project experience, generate context-free next-session prompt. Use when: "дизайн ретроспектива", "design retrospective", "уроки дизайна"…
skill-trainer
Embeds accumulated triads from quick-learning into target skills as permanent instructions. Reads triads with Adapted=— from triad-index.md, analyzes each skill's existing logic, auto-applies new rules when no coverage exists, proposes refinements when partial coverage found. After embedding, updates Adapted field and…
quick-learning
Owner of the unified methodology knowledge system: format, triad structure, similarity check, Seen counters, and Adapted tracking. Signal-gated: skips clean sessions automatically (zero cost). Automatic trigger: called by feature-execution, do-task, and design-generate (context exhaustion). Use when: "quick learning"…
oma-explanation
Turn a code change (diff, PR, branch, commit range) into a rich, self-contained interactive HTML explainer with Background / Intuition / Code / Quiz sections. Use for explain, walkthrough, code-change explanation, diff/PR/branch explainer requests — 설명서, 해설, コード解説, 代码讲解. Produces a single offline-capable HTML file…
paper-graph
Use this skill to map the genealogical lineage and historical progression of a research field. It is designed to visualize the evolutionary path of ideas, showing how technical challenges in earlier works were addressed by subsequent research improvements. The final deliverable is a Markdown file with embedded Mermaid…
map-understand
Interactive deep-understanding and quiz mode for MAP sessions. Use when the user wants to understand code, a diff, workflow result, debugging cause, or architecture and be checked with restatements or quizzes.