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 skills add takashicompany/headlenss --skill headlenss-dev-servergit clone --depth 1 https://github.com/takashicompany/headlenssWrote 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/takashicompany/headlenss/headlenss-dev-server)<a href="https://agentmods.dev/skills/takashicompany/headlenss/headlenss-dev-server"><img src="https://agentmods.dev/badge/skills/takashicompany/headlenss/headlenss-dev-server/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/takashicompany/headlenss/headlenss-dev-server"><img src="https://agentmods.dev/badge/skills/takashicompany/headlenss/headlenss-dev-server.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 | $0.00000 | $0.02239 |
| Opus 5 | $0.00000 | $0.01120 |
| Sonnet 5 | $0.00000 | $0.00448 |
| Haiku 4.5 | $0.00000 | $0.00224 |
Grade B, and why
headlenss-dev-server scanned grade B with 2 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo tailscale serve status Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w "%{http_code}\n" http://127.0.0.1:3000/api/health How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
headlenss のマシンで dev server を立てる
headlenss が動いているマシンは、外部からその PC を操作するための生命線になっている。 headlenss が使っているポートを奪わずに自分の dev server を tailnet 公開するための手順。
このスキルは環境非依存。ホスト名・ポートはすべて置き換える前提の例。まず「0. 環境を調べる」で 実際の値を確定させること。推測しない。
必ず守る制約 (= headlenss を汚さない)
典型的な構成では headlenss が次を占有している (手順 0 で実際の値を確認する)。
| ポート | 用途 |
|---|---|
| 3000 | headlenss サーバ本体 (systemd ユーザーサービス headlenss 等で常駐) |
| 443 / 80 | tailscale serve が headlenss サーバへ流す https / http ルート (公開している場合) |
- headlenss が使っているポートを奪わない。
:3000を listen しているプロセスをlsof/ssで見つけても kill しない。 tailscale serve resetを使わない。 全ポートの設定を消すので headlenss も巻き込む。tailscale serve --bg <target>(=--https=省略) を使わない。 既定で:443を 上書きし、headlenss のルートを奪う。- 公開ルートに割り当てられているポート (既定
:443/:80) を--https=/--http=の 対象にしない。
これらを事故で打たないよう、Claude Code の permissions で tailscale serve 系を ask
(確認プロンプト) にしておくとよい。
入力
<port>: 使いたいポート番号 (5173, 8080, 8443 など)。headlenss の占有ポートと、 既に listen 中のポートを避けて選ぶ (手順 0・1)。- HTTPS が必要か?
- Even WebView の secure context (getUserMedia, clipboard, Service Worker など) を使う → YES (HTTPS 必須)
- ブラウザでの見た目確認だけ → NO (HTTP で OK)
0. 環境を調べる (最初に必ずやる)
# headlenss サーバのポート (既定 3000) が生きているか
curl -s -o /dev/null -w "%{http_code}\n" http://127.0.0.1:3000/api/health
# tailnet 上のホスト名
tailscale status --json | python3 -c "import json,sys; print(json.load(sys.stdin)['Self']['DNSName'].rstrip('.'))"
# 既に tailscale serve で公開されているポート (= 触ってはいけない行)
sudo tailscale serve status
以後、ホスト名を <host>.<tailnet>.ts.net と書く。tailscale serve status の出力は
作業前に控えておく (後で「奪っていないこと」を照合するため)。
1. ポート空き確認
ss -tlnp 2>/dev/null | grep ":<port> " || echo "port <port> is free"
埋まっていたら別のポートを選ぶ。先客のプロセスを止めない。 headlenss のポートが 出てきたら絶対に触らない。
2. dev server を 0.0.0.0 で起動
localhost (= 127.0.0.1) だけにバインドすると tailnet 経由では届かない。必ず 0.0.0.0
(or --host) を指定する。
| ツール | コマンド例 |
|---|---|
| Vite | npx vite --host --port <port> --strictPort |
| Next.js | next dev -H 0.0.0.0 -p <port> |
| Bun (Hono 等) | PORT=<port> bun --hot src/index.ts (or サーバコードで 0.0.0.0 明示) |
| Python 簡易 | python3 -m http.server <port> --bind 0.0.0.0 |
| Node static | npx serve -l tcp://0.0.0.0:<port> dist/ |
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 · 156 lines · 0 tokens per session scan B 9f439e486e17
headlenss-dev-server is a skill published in the GitHub repository takashicompany/headlenss (5 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,239 tokens. A static security scan graded it B with 2 findings (asks for root, 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…