Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/sunghyun-k/claude-swift-plugins/spi-docs)<a href="https://agentmods.dev/skills/sunghyun-k/claude-swift-plugins/spi-docs"><img src="https://agentmods.dev/badge/skills/sunghyun-k/claude-swift-plugins/spi-docs/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/sunghyun-k/claude-swift-plugins/spi-docs"><img src="https://agentmods.dev/badge/skills/sunghyun-k/claude-swift-plugins/spi-docs.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 | $0.00059 | $0.01127 |
| Opus 5 | $0.00030 | $0.00563 |
| Sonnet 5 | $0.00012 | $0.00225 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
spi-docs 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 9d 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.
SPI 는 Cloudflare managed challenge("Just a moment…") 뒤에 있어서 `curl`, `requests`, `WebFetch` 같은 순수 HTTP 클라이언트는 **403** 으로 막힙니다. JS 를 실행하는 실제 브라우저 엔진으로 챌린지를 통과한 뒤, **같은 오리진(same-origin) `fetch`** 로 DocC 데이터 JSON 을 받아야 합니다. How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swift Package Index 문서 → 마크다운
swiftpackageindex.com 의 DocC 문서 페이지를 깔끔한 마크다운으로 변환해 읽는 스킬입니다. 변환된 문서의 Topics / See Also 링크는 모두 다시 이 스킬로 열 수 있는 SPI 문서 URL 이라, 링크를 따라가며 문서를 탐색할 수 있습니다.
언제 쓰나
https://swiftpackageindex.com/{owner}/{repo}/{ref}/documentation/...형태의 URL 이 주어졌을 때- "이 Swift 패키지 문서 읽어줘", "GRDB 문서 요약해줘" 등 SPI 문서 열람이 필요할 때
왜 브라우저가 필요한가
SPI 는 Cloudflare managed challenge("Just a moment…") 뒤에 있어서 curl, requests, WebFetch 같은 순수 HTTP 클라이언트는 403 으로 막힙니다. JS 를 실행하는 실제 브라우저 엔진으로 챌린지를 통과한 뒤, 같은 오리진(same-origin) fetch 로 DocC 데이터 JSON 을 받아야 합니다. 그래서 이 스킬은 세션의 브라우저 도구를 사용합니다.
- 우선순위 1: 인앱 브라우저 —
mcp__Claude_Browser__*(javascript_tool,preview_start,computer) - 대안: Chrome 확장 —
mcp__claude-in-chrome__javascript_tool(동일한 JS 를 실행)
둘 다 없으면 이 스킬은 동작하지 않습니다. 그 경우 사용자에게 브라우저 도구가 필요함을 알리세요.
절차
1. Cloudflare 통과 (세션당 1회)
브라우저 탭을 아무 SPI 문서 URL 로 엽니다. 이미 swiftpackageindex.com 이 열려 있으면 건너뜁니다.
preview_start { "url": "<사용자가 준 SPI 문서 URL>" }
여는 직후 "잠시만 기다리십시오…"(Cloudflare) 페이지가 뜰 수 있으니 2~3초 대기 후 진행합니다.
computer { "action": "wait", "duration": 3 }
탭이 실제 문서 제목(예: "GRDB | Documentation")으로 바뀌면 통과된 것입니다.
2. 변환기 주입 (탭당 1회)
${CLAUDE_PLUGIN_ROOT}/skills/spi-docs/docc2md.js 파일을 Read 로 읽어, 그 전체 내용을 그대로 브라우저의 javascript_tool 에 text 로 실행합니다. 이 스크립트는 window.__spiDocc 를 정의합니다.
탭을 새로고침하거나 다른 오리진으로 이동하면
window.__spiDocc가 사라지므로 다시 주입합니다. 같은 탭·같은 오리진에 머무는 한 재주입 불필요.
3. 페이지 변환
원하는 SPI 문서 URL 로 convert 를 호출하고, 반환된 마크다운을 사용자에게 출력합니다.
window.__spiDocc.convert("https://swiftpackageindex.com/groue/GRDB.swift/master/documentation/grdb").then(r => r.markdown)
반환값은 { url, title, markdown } 입니다. 보통 .then(r => r.markdown) 로 마크다운만 받으면 됩니다.
4. 참조 링크 따라가기
출력된 마크다운의 ## Topics / ## See Also 링크는 전부 SPI 문서 URL 입니다. 다른 페이지를 읽으려면 그 URL 로 3번(같은 탭이면 주입 없이)만 다시 호출하면 됩니다.
URL 형태 참고
- 사람용 문서 URL:
.../{owner}/{Repo}/{ref}/documentation/...(예:groue/GRDB.swift/master/documentation/grdb) convert는 내부적으로 데이터 엔드포인트.../{owner}/{repo-소문자}/{ref}/data/documentation/....json를 계산해 fetch 합니다. 사용자에게 보이는 문서 URL 을 그대로 넘기면 됩니다.master,main, 태그, 버전 등 어떤 ref 든 동작합니다.
What ships with it
1 file 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.
- 9d ago First seen · 74 lines · 59 tokens per session scan A 302548aaf83d
spi-docs is a skill published in the GitHub repository sunghyun-k/claude-swift-plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,127 once invoked, about $0.0003 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
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…