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-g2-plugingit 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-g2-plugin)<a href="https://agentmods.dev/skills/takashicompany/headlenss/headlenss-g2-plugin"><img src="https://agentmods.dev/badge/skills/takashicompany/headlenss/headlenss-g2-plugin/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-g2-plugin"><img src="https://agentmods.dev/badge/skills/takashicompany/headlenss/headlenss-g2-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Supply Chain · line 61 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
- high Privilege Escalation · line 91 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Supply Chain · line 306 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00191 | $0.05281 |
| Opus 5 | $0.00096 | $0.02641 |
| Sonnet 5 | $0.00038 | $0.01056 |
| Haiku 4.5 | $0.00019 | $0.00528 |
Grade A, and why
headlenss-g2-plugin 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 12d 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.
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 — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
開発中の G2 プラグインを headlenss から開けるようにする
headlenss (app 2.5.0 以降) は、tmux セッションのフォルダに置かれた宣言ファイルを読み、 そのセッションの下に G2 プラグインをぶら下げて表示する。グラスの一覧からタップすると WebView ごとそのプラグインへ遷移する。
myproject [Claude] さっきの続きだけど…
▶ └ MyPlugin ← ここでタップすると開く
QR の再スキャンなしに開発中プラグインを開けるのが目的。
このスキルは環境非依存。 例に出てくるホスト名・ポート・パスはすべて置き換える前提で 書いてある。まず「0. 環境を調べる」で自分の環境の値を確定させること。
絶対に守ること
-
ポート番号から「自分のサーバ」と判断しない。 中身を取得して自分のものか確かめる (手順 3)。複数プロジェクトが同じポートを直書きしている事故が実際に起きている
-
他プラグインの環境を壊さない。 ポートが埋まっていたら自分が別のポートへ移る。 相手の dev server を落とす・設定を書き換える・共有ファイルの他人の行をいじる、はしない
-
自分のプラグインの画面が出るのを見るまで「できた」と言わない (手順 4-(3))
-
プロセスを kill しない。 共有プロキシを
kill/pkill/killall/ PID 指定の シグナルで止めない。psやssで得た親 PID・祖先 PID は診断情報であって停止対象では ない。子プロセスを止めたいからといって、親や祖先を kill しない以下は絶対に停止対象に含めない:
/usr/lib/systemd/systemd --user(ユーザーマネージャ本体)- cgroup が
user@<uid>.service/init.scopeのプロセス - tmux サーバー
headlenss.service- 自分が起動していない共有サービス全般
正常手順 (後述の
systemctl --user restart) が失敗したら、代替の kill 手段を 発明せず、作業を止めてユーザーに確認する。実際に起きた事故: 「設定を変えたらプロキシを再起動する」という手順に従い、稼働中 プロキシの PID を
psの祖先チェーンで遡って node → sh → npm → systemd --user と まとめて kill した。末端が PID 1133 = systemd ユーザーマネージャ本体だったため、 ユーザーセッション全体 (headlenss、tmux 全 27 セッション) が落ちた。
0. 環境を調べる (最初に必ずやる)
以下を確定させてから先へ進む。推測しない。
headlenss サーバのアドレス
グラス側アプリの設定に入っている URL。サーバ側からは systemd / プロセスで確認できる。
systemctl --user status headlenss 2>/dev/null | head -3 # 常駐しているか
curl -s -o /dev/null -w "%{http_code}\n" http://127.0.0.1:3000/api/health
外から見えるアドレスは公開方法による。tailscale なら:
tailscale serve status
tailscale status --json | python3 -c "import json,sys; d=json.load(sys.stdin); print(d['Self']['DNSName'].rstrip('.'), d['Self']['TailscaleIPs'][0])"
リポジトリの場所
# headlenss (サーバ + G2 アプリ)
# [email protected]:takashicompany/headlenss.git
# Plugin Loader (シム注入プロキシ。戻る動作に使う)
# [email protected]:takashicompany-org/plugin-loader.git
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.
- 12d ago First seen · 398 lines · 191 tokens per session scan A 81962a9d7486
headlenss-g2-plugin is a skill published in the GitHub repository takashicompany/headlenss (5 stars, last pushed 3d ago), licensed MIT. It adds 191 tokens to every session and 5,281 once invoked, about $0.0010 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
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.