Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/team-attention/plugins-for-claude-nativesnpx agentmods add skills/team-attention/plugins-for-claude-natives/kakaotalkWrote 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/team-attention/plugins-for-claude-natives/kakaotalk)<a href="https://agentmods.dev/skills/team-attention/plugins-for-claude-natives/kakaotalk"><img src="https://agentmods.dev/badge/skills/team-attention/plugins-for-claude-natives/kakaotalk/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/team-attention/plugins-for-claude-natives/kakaotalk"><img src="https://agentmods.dev/badge/skills/team-attention/plugins-for-claude-natives/kakaotalk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.01104 |
| Opus 5 | $0.00031 | $0.00552 |
| Sonnet 5 | $0.00012 | $0.00221 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
kakaotalk 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 11d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KakaoTalk CLI
macOS에서 CLI를 통해 카카오톡 메시지를 읽고 보내는 스킬.
트리거
- "카카오톡 메시지", "카톡 읽어줘", "~에게 메시지 보내줘"
스크립트 구조
| 파일 | 용도 |
|---|---|
kakao_read.py |
채팅방 검색, 열기, 메시지 읽기 |
kakao_send.py |
메시지 발송 |
메시지 발송 워크플로우
Step 1: 채팅방 열고 대화 내역 읽기
대상 이름으로 채팅방을 열고 대화 내역을 읽습니다:
uv run python .claude/skills/kakaotalk/scripts/kakao_read.py "대상이름" --json
출력 예시:
{
"chat_name": "구봉",
"messages": [
{"sender": "나", "text": "오늘 저녁 뭐 먹을까?", "time": "오후 3:24"},
{"sender": "구봉", "text": "파스타 어때?", "time": "오후 3:45"}
]
}
메시지 분석 시 주의:
- 배열 끝부분이 최신 메시지 (최근일수록 가치 높음)
- 1주일 이상 된 내용은 상황이 바뀌었을 수 있음
- 최근 대화 주제와 자연스럽게 이어지는 메시지 작성
Step 2: 맥락 파악 후 메시지 작성
읽은 대화 내역을 바탕으로:
- 최근 대화 흐름 파악
- 사용자 요청에 맞는 메시지 초안 작성
- 자연스럽고 맥락에 맞는 내용 구성
Step 3: 사용자 확인 (필수)
먼저 텍스트로 메시지 내용을 보여준 후 AskUserQuestion으로 확인:
[텍스트 출력]
**최근 대화 요약:**
- {최근 대화 내용 요약}
**보낼 메시지:**
받는 사람: {채팅방}
---
{메시지 내용}
sent with claude code
---
[AskUserQuestion]
질문: "이 메시지를 보낼까요?"
옵션: ["보내기", "수정 필요"]
Step 4: 발송
사용자 확인 후 메시지 발송:
uv run python .claude/skills/kakaotalk/scripts/kakao_send.py "채팅방이름" "메시지"
메시지 읽기 전용 워크플로우
단순히 대화 내역만 확인할 때:
uv run python .claude/skills/kakaotalk/scripts/kakao_read.py "대상이름" --json
읽은 후 사용자에게 요약 제공:
- 최근 대화 2-3개 요약
- 현재 진행 중인 대화 주제
- 답장이 필요한 내용이 있는지
CLI 옵션 레퍼런스
kakao_read.py
# 기본: 채팅방 열고 메시지 읽기
kakao_read.py "채팅방이름" [--limit N] [--json]
# 채팅 목록
kakao_read.py --list [--json]
# 검색
kakao_read.py --search "검색어" [--json]
# 읽고 창 닫기
kakao_read.py "채팅방이름" --close
kakao_send.py
# 기본 (서명 포함)
kakao_send.py "채팅방" "메시지"
# → "메시지\n\nsent with claude code"
# 서명 없이
kakao_send.py "채팅방" "메시지" --no-signature
# 보내고 창 닫기
kakao_send.py "채팅방" "메시지" --close
예시 시나리오
"구봉한테 보낼 메시지 제안"
[Step 1] 채팅방 열고 읽기
uv run python .../kakao_read.py "구봉" --json
[Step 2] 맥락 파악
최근 대화: 저녁 메뉴 논의 중
[Step 3] 메시지 제안
"파스타 좋아! 오늘 7시에 만날까?"
[Step 4] 사용자 확인 후 발송
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.
- 11d ago First seen · 162 lines · 62 tokens per session scan A 2f17e4bf52ef
kakaotalk is a skill published in the GitHub repository team-attention/plugins-for-claude-natives (824 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 1,104 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…