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/contentscoin/qrcoding-skill-mcp/qrcoding-connectnpx skills add contentscoin/qrcoding-skill-mcp --skill qrcoding-connectgit clone --depth 1 https://github.com/contentscoin/qrcoding-skill-mcpWrote 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/contentscoin/qrcoding-skill-mcp/qrcoding-connect)<a href="https://agentmods.dev/skills/contentscoin/qrcoding-skill-mcp/qrcoding-connect"><img src="https://agentmods.dev/badge/skills/contentscoin/qrcoding-skill-mcp/qrcoding-connect.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 | $0.00036 | $0.00775 |
| Opus 5 | $0.00018 | $0.00387 |
| Sonnet 5 | $0.00007 | $0.00155 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
qrcoding-connect scanned grade A 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/contentscoin/qrcoding-skill-mcp/main/install.sh -o /tmp/qrcoding-install.sh What it actually says
QR Coding Connect
QR Agent Studio MCP/스킬을 사용 중인 AI 클라이언트에 연결한다. 연결만 다루며, 실제 QR 작업은 qrcoding-campaign-operator로 위임한다.
공통
- Hosted MCP Gateway:
https://qrcoding-skill-mcp.vercel.app/mcp - API key는 QR Agent Studio 대시보드의 Skills & MCP / Connect 패널에서 발급하며
qras_로 시작한다. - Claude Code·Codex:
x-api-key헤더 또는QRCODING_API_KEY환경변수로 인증한다. 키를 답변·로그·public URL에 노출하지 않는다. - ChatGPT: 헤더 인증을 지원하지 않으므로 키를 커스텀 커넥터 URL 경로(
/mcp/<키>)에 넣고No authentication으로 연결한다. 그 URL은 비밀번호처럼 취급한다(아래 ChatGPT 섹션). - 설치 스크립트는 내려받아 내용을 확인한 뒤 실행한다.
curl -fsSL https://raw.githubusercontent.com/contentscoin/qrcoding-skill-mcp/main/install.sh -o /tmp/qrcoding-install.sh
cat /tmp/qrcoding-install.sh
Claude Code
bash /tmp/qrcoding-install.sh --claude --mode=ops --skip-key
설치 후 Claude Code를 완전히 종료했다가 다시 시작한다. QRCODING_API_KEY를 환경에 설정한다.
Codex
bash /tmp/qrcoding-install.sh --codex --mode=ops --skip-key
설치 후 Codex를 재시작한다.
ChatGPT
유료 플랜 + 데스크톱 웹에서 커스텀 커넥터로 연결한다. OAuth/구글 로그인이나 별도 터널은 필요 없다.
- 대시보드 Connect 패널에서 키를 발급하고 ChatGPT용 커넥터 URL 전체를 복사한다. URL은
…/mcp/<발급키>형태로 키가 경로에 포함된다. - ChatGPT → 설정 → Connectors → Developer mode → Add custom connector.
- 복사한 URL을 붙여넣고 Authentication을
No authentication으로 선택한 뒤 Connect. - 연결되면 새 대화에서 QR 생성·검증·수정을 자연어로 요청한다.
주의: 그 커넥터 URL은 키를 담고 있으므로 비밀번호처럼 다루고, 유출되면 대시보드에서 해당 키를 폐기한다. "Add custom connector"가 안 보이면 요금제·workspace 관리자 권한·데스크톱 웹 여부를 확인한다(모바일 미지원).
설치 구성
--mode=ops(기본): 운영 + 빠른시작 + 디자인 + 분석 + 연결 스킬.--mode=dev: 연동 설계(integration-architect) + 연결 스킬.--mode=full: 전체.
연결이 끝나면 "QR 만들어줘"는 qrcoding-quickstart, 분석은 qrcoding-analytics, 디자인은 qrcoding-designer가 받아 qrcoding-campaign-operator로 위임한다.
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.
- 4d ago First seen · 59 lines · 36 tokens per session scan A e6e647be0532
qrcoding-connect is a skill published in the GitHub repository contentscoin/qrcoding-skill-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 775 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
baoyu-article-illustrator
Article illustrations: type × style × palette consistency.
openhands
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
agentmail
Use when an agent needs AgentMail CLI email inboxes.
mcporter
List, auth, and call MCP servers/tools from the terminal.
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".