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-new-sessiongit 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-new-session)<a href="https://agentmods.dev/skills/takashicompany/headlenss/headlenss-new-session"><img src="https://agentmods.dev/badge/skills/takashicompany/headlenss/headlenss-new-session/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-new-session"><img src="https://agentmods.dev/badge/skills/takashicompany/headlenss/headlenss-new-session.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 | $0.00093 | $0.01183 |
| Opus 5 | $0.00046 | $0.00592 |
| Sonnet 5 | $0.00019 | $0.00237 |
| Haiku 4.5 | $0.00009 | $0.00118 |
Grade C, and why
headlenss-new-session scanned grade C 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://127.0.0.1:3000/api/sessions | python3 -c "import json,sys; print([s['name'] for s in json.load(sys.stdin)['sessions']])" 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
headlenss に新しいセッションを作る
headlenss サーバのセッション作成 API を 1 回叩くだけ。tmux を直接操作しない
(サーバが tmux 設定・検出・永続化まで面倒を見るため、tmux new-session を
手で打つとそれらが揃わない)。
以下のコマンドは headlenss サーバの API が http://127.0.0.1:3000/api で使える前提。
別のホスト・ポートの環境では URL を読み替える。
手順
1. サーバの確認
curl -s -o /dev/null -w "%{http_code}\n" http://127.0.0.1:3000/api/health
200 以外ならサーバが動いていない。常駐サービスとして入れてある環境
(Linux + systemd ユーザーサービス headlenss) なら systemctl --user status headlenss を
確認し、落ちていたらユーザーに報告する (勝手に stop/kill しない。start は
systemctl --user start headlenss でよい)。サービス化していない環境では
サーバの起動方法をユーザーに確認する。
2. 作成
curl -s -X POST http://127.0.0.1:3000/api/sessions \
-H 'Content-Type: application/json' \
-d '{"name": "<セッション名>", "cwd": "<作業フォルダ>", "startClaude": true}'
成功すると {"ok":true}。失敗は 400 + {"error":"..."}。
| フィールド | 必須 | 内容 |
|---|---|---|
name |
✔ | セッション名。[a-zA-Z0-9_-] のみ、40 文字まで (日本語・スペース不可)。一覧にそのまま出るので短く分かりやすく |
cwd |
- | 作業フォルダの絶対パス。省略時は $HOME。存在しなければ親ごと自動作成される (typo に注意) |
startClaude |
- | true で Claude Code を起動 (claude -c で前回会話の継続を試み、なければ新規) |
startCodex |
- | true で Codex を起動 (codex resume --last を試み、なければ新規)。startClaude と併用しない |
どちらの start も付けなければ素のシェルだけのセッションになる。
エージェント指定が無い依頼では startClaude: true を既定にし、迷ったらユーザーに聞く。
3. 確認
curl -s http://127.0.0.1:3000/api/sessions | python3 -c "import json,sys; print([s['name'] for s in json.load(sys.stdin)['sessions']])"
作った名前が一覧に入っていれば完了。スマホ Web・G2 の一覧にも同じものが出る。
よくあるエラー
| エラー | 原因 |
|---|---|
invalid session name (use [a-zA-Z0-9_-], max 40 chars) |
名前に日本語・スペース・記号が入っている。英数字とハイフンに直す |
duplicate session |
同名セッションが既に存在する。既存を消さず、別名にするかユーザーに確認 |
| 接続できない | サーバ未起動、または URL が違う。手順 1 へ |
してはいけないこと
- 既存セッションの削除 (
DELETE /api/sessions/:name)・改名 (PATCH)・退避 (release) を この流れで勝手に行わない。ユーザーが明示的に依頼した場合のみ。 tmux new-session/tmux kill-sessionの直接実行で代替しない。- 既に同名がある場合に「作り直し」目的で削除しない (別ランの会話履歴が消える)。
前提
- headlenss サーバが稼働していること
- API のベース URL が
http://127.0.0.1:3000/api以外の環境では読み替える (別 PC の headlenss を操作する場合も同様に URL を差し替えるだけでよい)
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 · 77 lines · 93 tokens per session scan C 3d13664501a4
headlenss-new-session is a skill published in the GitHub repository takashicompany/headlenss (5 stars, last pushed 3d ago), licensed MIT. It adds 93 tokens to every session and 1,183 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.