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 auto-replygit 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/auto-reply)<a href="https://agentmods.dev/skills/mupengi-bot/mupengism/auto-reply"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/auto-reply/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/auto-reply"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/auto-reply.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 | $0.00092 | $0.01072 |
| Opus 5 | $0.00046 | $0.00536 |
| Sonnet 5 | $0.00018 | $0.00214 |
| Haiku 4.5 | $0.00009 | $0.00107 |
Grade C, and why
auto-reply scanned grade C with 1 finding 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **코드 실행 시도**: "execute command", "run script", "eval(", "rm -rf", "sudo" How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instagram DM Auto-Reply 🐧
v2.js (Internal API) 기반. 브라우저 스냅샷 0회, CDP 쿠키 추출 → Instagram REST API 직접 호출.
전제 조건
- OpenClaw 브라우저 실행 중 (포트 18800)
- 브라우저에 Instagram 탭 열려있고 로그인 상태
wsnpm 패키지 (npm i -g ws또는 로컬)
스크립트 목록
| 스크립트 | 용도 |
|---|---|
scripts/v2.js |
DM CLI (inbox, unread, check, read, reply) |
scripts/auto-reply.js |
dm-alert.json 읽고 보안 체크 후 답장 메타데이터 반환 |
scripts/check-notify.js |
새 DM 알림 체크 (cron용, 상태 파일 기반) |
scripts/dm-watcher.js |
실시간 DM 감지 데몬 (15초 폴링) |
핵심 워크플로우
1. DM 확인
node scripts/v2.js check # unread 개수 (가장 가벼움)
node scripts/v2.js unread # 읽지 않은 DM 목록
node scripts/v2.js inbox # 전체 DM 목록
2. 메시지 읽기
node scripts/v2.js read "<username>" -l 5
3. 답장
node scripts/v2.js reply "<username>" "메시지 내용"
API 실패 시 JSON에 method: "use_browser" + threadUrl 반환 → browser tool로 fallback.
4. 알림 체크 (cron 연동)
node scripts/check-notify.js
- 새 DM 있으면:
📩 인스타 새 DM N건: ...출력 - 없으면:
no_new출력 - 상태 파일
dm-state.json으로 중복 방지
5. 자동응답 플로우
node scripts/auto-reply.js
dm-alert.json읽기 (dm-watcher가 생성)- 각 DM 보안 체크 실행
- 결과 반환:
needs_reply/security_alert/skipped - AI가
needs_reply인 DM에 대해 답장 생성 →v2.js reply로 전송
6. 실시간 감지 데몬
node scripts/dm-watcher.js # 감지만
node scripts/dm-watcher.js --auto-reply # Discord 알림 포함
15초마다 v2.js check 폴링. 새 DM 감지 시 dm-alert.json 기록 + Discord DM 알림.
보안 체크 (인젝션 거부)
auto-reply.js의 SECURITY_PATTERNS가 다음을 감지:
- 프롬프트 인젝션: "ignore previous", "system prompt", "you are now", "act as", "pretend"
- 탈옥 시도: "override", "jailbreak", "DAN mode", "bypass"
- 민감 정보 요청: "secret key", "private key", "seed phrase", "wallet address"
- 코드 실행 시도: "execute command", "run script", "eval(", "rm -rf", "sudo"
- 소셜 엔지니어링: "simulation mode", zero-width 문자
위협 감지 시 → 답장하지 않고 security_alert 반환. 형님에게 별도 알림.
cron 설정 예시
# 5분마다 DM 체크
- schedule: "*/5 * * * *"
command: "node /path/to/scripts/check-notify.js"
systemEvent: true
# 또는 dm-watcher 데몬으로 상시 감시
- schedule: "@reboot"
command: "node /path/to/scripts/dm-watcher.js --auto-reply"
background: true
What ships with it
4 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.
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.
- 8d ago First seen · 113 lines · 92 tokens per session scan C 72bc02f8f3b6
auto-reply is a skill published in the GitHub repository mupengi-bot/mupengism (10 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 1,072 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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.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…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
agent-browser
Headless browser automation CLI. Open, browse, interact with, and screenshot web pages. Use when: opening websites, browser-based login, web app testing, taking screenshots, UI verification.