retroweb

retroweb is a skill for Claude Code, Codex from 1llum1n4t1s/Retroweb-MCP. It costs 141 tokens per session (3,535 once invoked), scanned A, original, MIT.

A guide for finding obscure personal websites from the 1990s and early 2000s through web archives. It uses old directories, link lists, web rings, and hosting services because many of these pages are missing from modern search indexes.

In plain words
What is it for?
Researching old GeoCities, Angelfire, Tripod, AOL, Japanese personal sites, and other vanished or hard-to-find pages.
Why use it?
It addresses the problem of finding archived sites that ordinary search engines do not list.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Researching old GeoCities, Angelfire, Tripod, AOL, Japanese personal sites, and other vanished or hard-to-find pages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/1llum1n4t1s/retroweb-mcp/retroweb
Install

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.

Any agent
npx skills add 1llum1n4t1s/Retroweb-MCP --skill retroweb
Clone the repo
git clone --depth 1 https://github.com/1llum1n4t1s/Retroweb-MCP

Made for: Claude Code, Codex.

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.

agentmods badge for retroweb

README.md
[![agentmods](https://agentmods.dev/badge/skills/1llum1n4t1s/retroweb-mcp/retroweb/github.svg)](https://agentmods.dev/skills/1llum1n4t1s/retroweb-mcp/retroweb)
Your own site
<a href="https://agentmods.dev/skills/1llum1n4t1s/retroweb-mcp/retroweb"><img src="https://agentmods.dev/badge/skills/1llum1n4t1s/retroweb-mcp/retroweb/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.

agentmods 80×15 button for retroweb

Your own site · 80×15
<a href="https://agentmods.dev/skills/1llum1n4t1s/retroweb-mcp/retroweb"><img src="https://agentmods.dev/badge/skills/1llum1n4t1s/retroweb-mcp/retroweb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,535 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00141 $0.03535
Opus 5 $0.00071 $0.01767
Sonnet 5 $0.00028 $0.00707
Haiku 4.5 $0.00014 $0.00353

Measured 7d ago against content hash 11f49e93d693, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

retroweb 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 7d 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.

skills/retroweb/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

レトロサイト発掘の手順

前提となる考え方

90 年代の個人サイトは 「検索」ではなく「ディレクトリとリンク集と Web リング」で発見される設計だった。 現代の検索エンジンを工夫しても届かないのは、索引が存在しないからで、クエリの問題ではない。

したがって取るべき戦略は 1 つ: 当時の発見経路をアーカイブ上で再生する

これは日本語圏でも海外でも変わらない。違うのはホスト名・URL の階層・当時の言い回しの 3 点で、 海外にだけ全文検索の抜け道(wiby_search)がある。

Retroweb MCP のツールはこの経路をなぞる順に並んでいる。迷ったら retro_search_strategy を呼ぶ (海外なら region="intl" を付ける)。

基本の流れ

1. 当たりを付ける(どのホストに居たか)

legacy_hosts で当時のホスティング一覧を得る。主題から置き場所を推測する。 region を指定しないと日本語圏と海外が混ざって返るjp / intl / us uk fr de it nl au / global)。

日本語圏:

主題 見るべきホスト
二次創作・CG・同人 geocities.co.jp(エリア別)、isweb.infoseek.co.jp
テキスト・日記 readme.jptesio.net(日記才人)、isweb
技術・研究 ac.jp/~user/asahi-net.or.jp/~user/bekkoame.ne.jp
何でも dir.yahoo.co.jp(人力ディレクトリ=最大の名簿)

海外:

主題 見るべきホスト
SF・ゲーム・オカルト www.geocities.com/Area51(本家のエリア名は主題に対応している)
アート・音楽・映画 www.geocities.com/SoHo /Hollywood /Viennawww.angelfire.com
技術・学術 www.geocities.com/SiliconValley /Athensedu/~user/ac.uk/~user/
個人の日常・家族 members.aol.comhometown.aol.comwww.geocities.com/Heartland
欧州語圏 homepages.demon.co.uk、独 home.t-online.de、仏 perso.wanadoo.fr / www.multimania.com、伊 digilander.iol.it
何でも dmoz.org(人力ディレクトリ=海外最大の名簿)、dir.yahoo.com

2. 個人サイトを直接列挙する ← 最も効く

discover_sites(url="www.geocities.co.jp/Playtown-Bingo", from="1998", to="2002")

これが主力。ホスティング配下に どんなサイトが実在したか をユーザー単位で一覧化する。 実測で 1 エリアから 148 サイトが出る。observedFiles が多いものほど中身が濃い。

エリア名が分からなければホスト名だけで呼んでよい。

discover_sites(url="www.geocities.co.jp", from="1997", to="2002")

索引全体へ散らして読むので、実在したエリア名が siteRoot に出てくる (実測: 12 エリアにまたがる 226 サイトが 6 秒)。ただし結果は網羅ではなく標本で、 coverage.sampledtrue になる。目当てのエリアが見えたら、そのエリアで呼び直すと深く掘れる。

ジオシティーズのエリア名は細分されている点に注意。Playtown だけでなく Playtown-Bingo Playtown-Denen のようなハイフン付きが本体。

海外は URL の階層が違う。

discover_sites(url="www.geocities.com/SoHo", from="1997", to="2001")   # 実測 163 サイト
discover_sites(url="www.angelfire.com", from="1999", to="2002")

Read the full file on GitHub · 198 lines

Changes

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.

  1. 7d ago Changed · +15 lines 11f49e93d693
  2. 10d ago First seen · 183 lines · 141 tokens per session scan A 7a63cb1f7e13

Subscribe to this mod's changes

retroweb is a skill published in the GitHub repository 1llum1n4t1s/Retroweb-MCP (0 stars, last pushed 4d ago), licensed MIT. It adds 141 tokens to every session and 3,535 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens