メニュー
One-time setup for AdGuard Home integration. Captures the AdGuard Home base URL, credentials, and target blocklist filename, validates connectivity, and persists to corpus/config.json. Use before adguard-push.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/danielrosehill/Claude-SpamHole-Plugin --skill adguard-configureコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Push the user's accumulated tracking-pixel + ad-tracker domains from the SpamHole corpus into a self-hosted AdGuard Home instance, using the credentials configured by adguard-configure. Network-layer block — every device on the LAN benefits, not just one mailbox. Use when the user wants to apply their corpus findings at the DNS layer.
Run the full SpamHole analysis pipeline on a single email — semantic spam reasoning, tracking-pixel detection, sender block, processed-emails log, markdown report. Use when the user wants a deep dive on one email rather than the lighter capture-spam-sample flow.
Create a server-side Gmail filter that auto-trashes (or labels + archives) future mail from a sender, via an available email MCP. Falls back to recording the block in the local sender-blocklist.json if no MCP is wired up. Use when the user says "block this sender" or "make sure I never see another email from X".
SOC 職業分類に基づく
SKILL.md を表示中
| name | adguard-configure |
| description | One-time setup for AdGuard Home integration. Captures the AdGuard Home base URL, credentials, and target blocklist filename, validates connectivity, and persists to corpus/config.json. Use before adguard-push. |
Wire SpamHole up to a self-hosted AdGuard Home instance so blocklist exports can be pushed network-wide.
Standard resolver ($CLAUDE_USER_DATA/spamhole/config.json → corpus_path). Run setup-corpus first if missing.
http://adguard.lan:3000 or https://dns.example.com. Must be reachable from this machine.custom-rules (default) — append to AdGuard Home's "User rules" via /control/filtering/set_rules. Best for small lists, fast iteration.hosted-list — host the export file somewhere reachable (HTTP) and add it as a managed blocklist URL via /control/filtering/add_url. Best for larger lists or sharing across instances.op-vault plugin if installed) over plaintext. If plaintext, store in <corpus>/config.json with explicit user consent and chmod 600.Probe GET <base>/control/status with Basic Auth to validate URL + credentials. Surface any TLS / 401 / connection-refused error to the user.
Read current filter state via GET <base>/control/filtering/status so the user can see what's already there before SpamHole touches it.
If strategy = hosted-list, ask where the blocklist file should be hosted (suggestions: a path served by a local nginx, a Cloudflare R2 bucket via the cloudflare-mgmt MCP, a private gist via gist-writer). Persist the URL.
Persist to <corpus>/config.json under an adguard key:
{
"adguard": {
"base_url": "http://adguard.lan:3000",
"username": "admin",
"password_ref": "op://Private/AdGuard Home/password",
"strategy": "custom-rules",
"list_name": "spamhole",
"hosted_url": null
}
}
Use password_ref (1Password URI) where possible. Only fall back to a password field with explicit user consent.
Report: connectivity OK, current filter count, chosen strategy, next step (adguard-push).