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 skills add mupengi-bot/mupengism --skill qjc-ai-insightsgit clone --depth 1 https://github.com/mupengi-bot/mupengismWrote 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/mupengi-bot/mupengism/qjc-ai-insights)<a href="https://agentmods.dev/skills/mupengi-bot/mupengism/qjc-ai-insights"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/qjc-ai-insights/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/mupengi-bot/mupengism/qjc-ai-insights"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/qjc-ai-insights.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.01521 |
| Opus 5 | $0.00019 | $0.00760 |
| Sonnet 5 | $0.00008 | $0.00304 |
| Haiku 4.5 | $0.00004 | $0.00152 |
Grade A, and why
AI 에이전트 운영 인사이트 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 13d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 에이전트 운영 인사이트 🐧
Claude Code Agent Teams, Opus 4.6, MCP 서버를 활용한 AI 에이전트 실전 운영 가이드
출처: qjc.ai (퀀텀점프클럽) Threads 계정 분석 참고: https://www.threads.com/@qjc.ai | 분석일: 2026-02-07
🎯 핵심 컨셉: 1인 기업 + 100개 AI 에이전트
"직원 수: 0명, AI 에이전트: 100개+"
qjc.ai는 혼자서 17개 부서(금융팀, 마케팅팀, 개발팀, 보안팀 등)를 Claude Code 안에서 운영 중. 3개월간 구축한 시스템으로 100명 규모 팀과 동등한 생산성 달성.
🤖 Claude Code Agent Teams 운영법
팀 구성 가이드라인
| 규모 | 용도 | 비고 |
|---|---|---|
| 3명 | PR 리뷰 | 가벼운 작업 |
| 5명 | 보안/성능/테스트 | 가성비 최적 |
| 10명+ | 대규모 프로젝트 | 비용/조율 난이도 급증 |
| 16명 | Rust 컴파일러 구현 | 실제 사례 |
핵심 원칙
- 파일 단위로 분리 - 2명이 같은 파일 편집하면 덮어쓰기 발생
- 5~6명이 공식 권장 - 일반적으로 3~5명이 가성비 최적
- tmux로 화면 분할 - 에이전트 5명 동시 작업 모니터링 가능
- 독립 컨텍스트 - 각 teammate가 1M 토큰 컨텍스트 사용
비용 고려사항
- 인원 비례 비용 증가
- broadcast 비용: 전체 메시지 전송 시 인원 × 비용
- Lead 조율 부담: 인원 많을수록 증가
🧠 Claude Opus 4.6 활용 전략
Adaptive Thinking (핵심 변화)
기존 budget_tokens 직접 지정 방식 → deprecated
새로운 effort 파라미터:
max: 최고 깊이 사고high: 기본값 (주의!)medium: 일반 작업low: 간단한 작업
⚠️ 비용 절약 핵심: 간단한 작업에 high(기본값) 쓰면 불필요한 사고 토큰 폭발 → 작업 복잡도에 맞게 effort 낮추기
프롬프팅 변화
- 기존 프롬프트 그대로 사용 시 과도한 도구 호출 폭발
- Opus 4.6은 프롬프팅 방식 자체를 재설계 필요
📏 Claude Code Rules 시스템
LLM 한계 극복법
문제: 날짜/달력 계산 정확도 26.3% (4번 중 3번 오답)
해결책: ~/.claude/rules/ 폴더에 마크다운 파일 생성
# date-calculation.md
## CRITICAL: 날짜 계산 규칙
날짜 계산은 절대 머리로 하지 말 것.
반드시 Bash나 Python 도구를 사용할 것.
예시:
- `date -d "+30 days"` (Bash)
- `datetime.now() + timedelta(days=30)` (Python)
💡 팁: "CRITICAL" 표시하면 준수율 훨씬 향상
🔌 MCP 서버 활용
개념
AI가 외부 데이터에 직접 접근하게 해주는 프로토콜. "AI에게 금융 데이터 파이프라인을 꽂아주는 것"
활용 예시
- 금, 은, 비트코인 실시간 가격 조회
- 금리 변화 비교 분석
- 투자 분석 데이터 자동 수집
"금 가격 추이랑 금리 변화 비교해줘" → 바로 데이터 뽑아서 분석
💰 금융/비즈니스 자동화
Claude Code로 자동화 가능한 금융 작업:
- DCF 밸류에이션
- 10분 VaR 리스크 분석
- 스타트업 재무 모델링 템플릿화
- 연례 보고서 분석 (PDF 던지면 끝)
"금융 전공 아니어도 됩니다"
📊 벤치마크 (2026년 2월 기준)
| 모델 | ARC-AGI-2 | SWE-bench |
|---|---|---|
| Claude Opus 4.6 | 68.8% | 80.8% |
| GPT-5.2 | 54.2% | - |
| Gemini 3 Pro | 45.1% | - |
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.
- 13d ago First seen · 174 lines · 39 tokens per session scan A 9db2778094b5
AI 에이전트 운영 인사이트 is a skill published in the GitHub repository mupengi-bot/mupengism (10 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 1,521 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 2026-08-31.
Other skills, from other repositories
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.writing-hive-skills
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.