doc-summarizer

doc-summarizer is a skill for Claude Code, Codex from BlackBeltTechnology/pi-agent-dashboard. It costs 105 tokens per session (1,141 once invoked), scanned A, original, MIT.

A document summarizer that extracts text from common files, splits large documents into manageable parts, and combines the results into one summary.

In plain words
What is it for?
Use it with PDF, DOCX, PPTX, XLSX, HTML, CSV, TXT, or Markdown files to extract their key information.
Why use it?
It lets you summarize files that are too large to read or fit into one context window, including scanned PDFs when optical character recognition is requested.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it with PDF, DOCX, PPTX, XLSX, HTML, CSV, TXT, or Markdown files to extract their key information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blackbelttechnology/pi-agent-dashboard/doc-summarizer
Install

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.

Any agent
npx skills add BlackBeltTechnology/pi-agent-dashboard --skill doc-summarizer
Clone the repo
git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for doc-summarizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/doc-summarizer/github.svg)](https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/doc-summarizer)
Your own site
<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/doc-summarizer"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/doc-summarizer/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.

agentmods 80×15 button for doc-summarizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/doc-summarizer"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/doc-summarizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,141 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00105 $0.01141
Opus 5 $0.00053 $0.00571
Sonnet 5 $0.00021 $0.00228
Haiku 4.5 $0.00011 $0.00114

Measured 9d ago against content hash 798c7b3563f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

doc-summarizer 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.

packages/document-converter/.pi/skills/doc-summarizer/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document Summarizer

Summarize documents of any size. Extraction goes through the document-converter engine facade (dc.convertToMarkdown) — the same Docker-quarantined engine the document-converter skill uses. There are NO host-side extractor scripts here; the facade is the only extraction surface. Chunking and synthesis are agent work.

Prerequisites

  • The document-converter package built and runnable: Docker available, image built (cd packages/document-converter && npm run build:image). See the document-converter SKILL for the full facade contract.
  • Nothing else. No pdftotext/pandoc/Python on the host — the engine owns all format handling inside Docker.

Step 1 — Extract to Markdown via the engine

Call the facade; never invoke Python, docling, or pdftotext directly.

import { createDocumentConverter } from "@blackbelt-technology/pi-dashboard-document-converter";
const dc = createDocumentConverter({ image: "pi-doc-engine:0.1.0", stagingDir: "/abs/staging" });

const { output } = await dc.convertToMarkdown("<file_path>");              // digital PDF/DOCX/…
// scanned PDF: pass OCR explicitly
await dc.convertToMarkdown("<file_path>", { ocr: { mode: "force", lang: ["english"] } });

The result is a provenance-stamped .md in stagingDir. Read that file to get the document text. On failure the call rejects with DocConverterError (.code, .stderr) — surface UNSUPPORTED_FORMAT, OCR_LANG_UNSUPPORTED, INGEST_FAILED, DOCKER_UNAVAILABLE rather than retrying blindly.

Step 2 — Decide direct vs. chunked

Measure the extracted Markdown:

  • < ~8,000 words (~10k tokens): summarize directly in the current context (Step 3a).
  • >= ~8,000 words: chunk and fan out (Step 3b).

Step 3a — Direct summarization (small documents)

Read the extracted .md and produce a summary using the output format below: title/subject, key points, entities, document type, language.

Step 3b — Chunked summarization (large documents)

Read the full file on GitHub · 116 lines

Changes

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.

  1. 9d ago First seen · 116 lines · 105 tokens per session scan A 798c7b3563f7

Subscribe to this mod's changes

doc-summarizer is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (278 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 1,141 once invoked, about $0.0005 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 2026-08-30.