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 thkt/dotclaude --skill transcribegit clone --depth 1 https://github.com/thkt/dotclaudeWrote 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/thkt/dotclaude/transcribe)<a href="https://agentmods.dev/skills/thkt/dotclaude/transcribe"><img src="https://agentmods.dev/badge/skills/thkt/dotclaude/transcribe/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/thkt/dotclaude/transcribe"><img src="https://agentmods.dev/badge/skills/thkt/dotclaude/transcribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.01485 |
| Opus 5.5 | $0.00023 | $0.00594 |
| Sonnet 5.5 | $0.00011 | $0.00297 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade A, and why
transcribe 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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/transcribe - スプレッドシート読み取り
Read ツールは xlsx を開けない。このリポジトリに入れた hucre をライブラリとして使い、シートを読む。
手順
- 中身の形を見る。
node ${CLAUDE_SKILL_DIR}/scripts/cli.ts list <xlsx>
シート一覧と充填率が出る。充填率は値が入っているセルの割合で、ここで次の分岐が決まる。
- 充填率で読み方を決める。
| 充填率 | 状態 | 読み方 |
|---|---|---|
| 20% 未満 | セル結合とレイアウト目的の空セルが大半を占める | extract で整形してから読む |
| 20% 以上 | 1 行 1 レコードに近い | --sheet でシートを絞り generic のまま extract する |
- 整形する。出力先はリポジトリの外か、ユーザーが指定した場所にする。
node ${CLAUDE_SKILL_DIR}/scripts/cli.ts extract <xlsx> --out <dir> [--profile <name>] [--sheet <n|name>]
- 欠落が無いか確かめる。この確認を飛ばさない。書式判定を誤るとエラーを出さずにセルが消えるため、消えたかどうかは照合でしか分からない。
node ${CLAUDE_SKILL_DIR}/scripts/cli.ts verify <xlsx> <dir>
OK: every cell of N sheets survived into the output. が出たら完了。欠落があればシート名と欠落セルの先頭 40 字を返すので、プロファイルの判定を直してから再実行する。
プロファイル
書式固有の判定はプロファイルが持つ。scripts/convert.ts の profiles に定義がある。
未知の書式にはまず generic を使う。表として整形したい場合だけプロファイルを足す。プロファイルが持つ判定は 5 つで、null にした判定は行わない。
| プロファイル | 対象 | 挙動 |
|---|---|---|
generic (既定) |
書式が不明なファイル | 表として解釈しない。セル結合を畳むだけで、情報は落ちない |
ja-api-spec |
項番とパラメータ名の列を持つ日本語の API 設計書 | 見出し、パラメータ表、2 段ヘッダ、コードブロックを復元する |
| キー | 判定 |
|---|---|
docHeaderFirstCell |
この文字列が A1 にあるとき、先頭 3 行を文書情報として畳む |
heading |
この正規表現に一致する 1〜2 セルの行を見出しにする |
tableHeadWords |
この正規表現に一致し、かつ 3 セル以上ある行を表ヘッダにする |
nestColumnLabel |
この語を含む列で、列内のセル位置を階層の深さとして復元する |
code |
この正規表現に一致する単独セルの行を連結してコードブロックにする |
What ships with it
2 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.
- 1mo ago Changed 5356a8283f3a
- 1mo ago First seen · 81 lines · 57 tokens per session scan A 1fb1c56c81c1
transcribe is a skill published in the GitHub repository thkt/dotclaude (12 stars, last pushed 25d ago), licensed MIT. It adds 57 tokens to every session and 1,485 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
paper-summarizer
Agents should invoke this skill for academic or technical papers, arXiv/PubMed/IEEE/ACM links, PDFs, methodology review, limitations, practical implications, or extracting findings for engineering decisions.
ln-25-architecture-diagram-builder
Creates evidence-backed current or target architecture diagrams; not UI design.
team-management-receiving-feedback
How to receive code review as technical evaluation rather than social performance — verify claims against the codebase before implementing, push back with evidence, and drop the performative agreement. Use when responding to a human reviewer, a PR comment, or another AI reviewer, and when deciding whether a suggestion…
review
Adversarial design review of a System Design Doc. Interrogates the staff questions, finds the cost-explosion and failure risks, returns a verdict. Sensors and evals gate.
compile-latex
Compile a .tex with latexmk and report ranked errors with file:line attribution across \input'd files, plus a diff against the last compile. TRIGGER on "compile this", "build my paper", "build the beamer deck", "why won't this compile", "what are the latex errors", "did my edit add warnings", or any request to build…
council
Five independent critic subagents in parallel on an idea, plan, design, R&R strategy, grant, or SKILL.md, then a synthesis pass that ranks findings by how much of the argument rests on them, never by vote count. A markdown work plan gets the plan roster (assumptions, pre-mortem, what to delete, alternatives per piece…