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/nonchan7720/manifold/webmcp-e2e)<a href="https://agentmods.dev/skills/nonchan7720/manifold/webmcp-e2e"><img src="https://agentmods.dev/badge/skills/nonchan7720/manifold/webmcp-e2e.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 5.1 | $0.00140 | $0.02281 |
| Opus 5 | $0.00070 | $0.01141 |
| Sonnet 5 | $0.00028 | $0.00456 |
| Haiku 4.5 | $0.00014 | $0.00228 |
Grade A, and why
webmcp-e2e scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebMCP Reverse Gateway E2E 結合確認
設計文書: docs/design/webmcp-reverse-gateway.ja.md
前提
tools/extension/、examples/webmcp-demo/、.claude/skills/webmcp-e2e/scripts/はいずれも pnpm パッケージ（pnpm install済みであること。scripts/は@modelcontextprotocol/sdkとplaywrightの実行用依存を持つ）- ポート: Manifold = 9999、デモページ = 5173（変更したら以降のコマンド・config を合わせる）
static モードの手順
1. 拡張をビルド
cd tools/extension && pnpm install && pnpm build # dist/ が生成される
cd .claude/skills/webmcp-e2e/scripts && pnpm install # e2e.mjs / create-pairing-code.mjs 用
2. Manifold を起動
mkdir -p examples/webmcp-reverse/tmp # sqlite.path: ./tmp/manifold.db 用
ENCRYPT_KEY=$(openssl rand -base64 32) go run . gateway --config examples/webmcp-reverse/config.yaml
- config は
examples/webmcp-reverse/config.yaml（gateway.port: 9999、edge auth は pairing + static、origin はhttp://localhost:5173）
3. デモページを起動
cd examples/webmcp-demo && pnpm dev # http://localhost:5173
document.modelContext に echo / get_current_time / increment_counter / decrement_counter が登録される。
4. ペアリングコードを取得
node .claude/skills/webmcp-e2e/scripts/create-pairing-code.mjs
edge.pairing.type: static（このスキルの config）では reverse サーバーへの/mcp/{name}に JWT ミドルウェア自体が掛からないため、Authorization ヘッダーは不要（スクリプトも送らない）- reverse サーバーはタブ未接続でも
create_pairing_codeツールだけは公開している（ベースサーバーが起動時に構築される）
5. 拡張入り Chromium を起動してペアリング
Playwright でヘッドフル Chromium を --load-extension=tools/extension/dist 付きで起動し、拡張 popup で edge URL（ws://localhost:9999/edge/ws）とコードを入力してペアリング。
6. 検証（scripts/e2e.mjs が一括実行）
node .claude/skills/webmcp-e2e/scripts/e2e.mjs
| 検証項目 | 期待結果 |
|---|---|
| タブ接続後の tools/list | create_pairing_code, echo, get_current_time, increment_counter, decrement_counter |
echo("...") |
入力文字列がそのまま返る |
increment_counter(by: 3) |
"3" が返り、ページ内カウンタ表示も一致 |
| タブを閉じて tools/call | isError: true + 「対象アプリのタブが開かれていません。…」の案内文 |
remote モードの手順
remote は identityKey を Bearer JWT(自前 JWKS で署名検証)から導出する。JWT を送るのは MCP クライアント(エージェント)側であり、拡張はペアリング(POST /edge/pair)のみ static と同じフローで、拡張自体の変更は不要。scripts/e2e-remote.mjs が JWKS サーバー起動・Manifold 起動・ペアリング・検証・プロセス終了までを一括で行う。
What ships with it
8 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.
- 6d ago First seen · 113 lines · 140 tokens per session scan A e720508ed7a3
webmcp-e2e is a skill published in the GitHub repository nonchan7720/manifold (4 stars, last pushed yesterday), licensed MIT. It adds 140 tokens to every session and 2,281 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.
Other skills, from other repositories
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
printing-press-reprint
Regenerate an existing printed CLI from scratch under the current Printing Press, with prior research, prior novel features, and prior patches (post-publish hand-fixes) carried into the writing pipeline as reconciliation context rather than dropped on the floor. Pulls the CLI from the public library if it isn't local…
printing-press-score
Score a generated CLI against the Steinberger bar, compare two CLIs side-by-side.
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by main printing-press SKILL.md (Phase 4.85) and printing-press-polish…
ble-session-appliance
Control BLE Session Appliance through the generated BLE device CLI.
ble-desk-lamp
Control BLE Desk Lamp through the generated BLE device CLI.