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 masa-san-jp/Agent-Aiko --skill extract-textgit clone --depth 1 https://github.com/masa-san-jp/Agent-AikoWrote 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/masa-san-jp/agent-aiko/extract-text)<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/extract-text"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/extract-text/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/masa-san-jp/agent-aiko/extract-text"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/extract-text.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 | $0.00159 | $0.01917 |
| Opus 5 | $0.00079 | $0.00958 |
| Sonnet 5 | $0.00032 | $0.00383 |
| Haiku 4.5 | $0.00016 | $0.00192 |
Grade A, and why
extract-text 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 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.
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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/extract-text
PDF と Google Workspace ファイルからテキストを抜き出す統合エントリ。入力の種類を判定し、専用ツールへ振り分ける。実装本体は持たず、pdf-extract と gws-read をオーケストレーションするだけの薄いラッパー。
ツール群は {{ORG_REPO_PATH}}/Agent-team/tools/ 配下に配置する前提。環境に合わせてパスは読み替える。
| 入力 | 振り分け先 |
|---|---|
ローカル PDF / Drive 上の PDF(application/pdf) |
{{ORG_REPO_PATH}}/Agent-team/tools/pdf-extract/ |
| Google ドキュメント / スプレッドシート / スライド(ネイティブ Google 形式) | {{ORG_REPO_PATH}}/Agent-team/tools/gws-read/(Slides は gslides-read) |
引数
| 引数 | 必須 | 意味 |
|---|---|---|
<input> |
○ | ローカルパス、Drive の ID または URL |
-o <path> |
× | 出力先ファイル。省略時は標準出力 |
--pages <範囲> |
× | PDF のページ指定(例:1-5,8) |
--page-markers |
× | PDF のページ境界マーカーを付与 |
入力の判定手順
- 入力がローカルに存在するパスか? → ローカルファイル
- 拡張子
.pdf→pdf-extractに--localで渡す - それ以外のローカルファイル(
.docx等)は対象外。別ツールを案内する
- 拡張子
- 入力が Drive の ID / URL か? → Drive ファイル
- URL に
/document//spreadsheets//presentation/が含まれる → それぞれ Docs / Sheets / Slides。gws-read(Slides はノート必要ならgslides-read)へ - 上記が判別できない(生 ID や
/file/d/の汎用 URL)→ まずpdf-extractに渡す。中で mimeType を確認し、PDF でなければ終了コード 4 で gws-read へ誘導されるので、その案内に従ってgws-readを実行する
- URL に
迷ったら pdf-extract を先に叩いてよい。PDF 以外の Google ファイルは自動で gws-read へ誘導される。
実行手順
setup(初回のみ)
bash {{ORG_REPO_PATH}}/Agent-team/tools/pdf-extract/setup.sh
bash {{ORG_REPO_PATH}}/Agent-team/tools/gws-read/setup.sh # Google ファイルを扱う場合
ローカル PDF だけなら認証不要。Drive 上のファイルを扱う場合は ADC(Application Default Credentials)が必要:
bash {{ORG_REPO_PATH}}/Agent-team/tools/pdf-extract/auth.sh # drive.readonly
PDF(ローカル / Drive)
{{ORG_REPO_PATH}}/Agent-team/tools/pdf-extract/pdf_extract.py /path/to/file.pdf
{{ORG_REPO_PATH}}/Agent-team/tools/pdf-extract/pdf_extract.py <drive-id-or-url>
{{ORG_REPO_PATH}}/Agent-team/tools/pdf-extract/pdf_extract.py <input> -o out.txt
{{ORG_REPO_PATH}}/Agent-team/tools/pdf-extract/pdf_extract.py <input> --pages 1-5,8
{{ORG_REPO_PATH}}/Agent-team/tools/pdf-extract/pdf_extract.py <input> --page-markers
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 · 109 lines · 159 tokens per session scan A 58c20992abea
extract-text is a skill published in the GitHub repository masa-san-jp/Agent-Aiko (3 stars, last pushed 1mo ago), licensed MIT. It adds 159 tokens to every session and 1,917 once invoked, about $0.0008 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
markitdown
Convert documents (PDF, Word, Excel, PowerPoint, images) to Markdown text for LLM processing.
doc-reader
Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the readdocument tool.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
xlsx
Build and edit professional Excel (.xlsx) spreadsheets, workbooks, and simple financial models — live formulas, number/date/currency formats, cell styling, conditional formatting, data-validation dropdowns, named ranges, frozen panes, merged cells, multi-sheet. Use when the user asks Brigade to make, fill, update…
Create and edit PDFs to a professional standard — generate from content, draw vector/precise layouts, embed custom (incl. CJK/Unicode) fonts, CREATE and fill AcroForm fields (text/checkbox/radio/dropdown), flatten, merge/split/rotate, stamp/watermark, encrypt, and extract text. Use when the user asks Brigade to make a…
unified-deliverable-workflow
Generate spreadsheets, diagrams, and PDF reports with iteration budgeting and error recovery.