import-summarizer

import-summarizer is a skill for Claude Code, Codex from RDEL-Group/compound-knowledge-work. It costs 99 tokens per session (1,079 once invoked), scanned A, original, MIT.

A skill for converting reference files into searchable summaries that use less working space for an AI agent.

In plain words
What is it for?
Process PDFs, Word files, PowerPoint files, web pages, text files, and Markdown into indexed summaries.
Why use it?
It avoids repeatedly handling large source files and makes their useful content easier to use as project context.

Skill for Claude CodeCodex

Part of the compound-knowledge-work plugin — 5 skills, 7 agents, 1 hook shipped together

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.

agentmods
npx agentmods add skills/rdel-group/compound-knowledge-work/import-summarizer
Any agent
npx skills add RDEL-Group/compound-knowledge-work --skill import-summarizer
Clone the repo
git clone --depth 1 https://github.com/RDEL-Group/compound-knowledge-work

Made for: Claude Code, Codex.

Or install compound-knowledge-work, the plugin that ships this one along with the rest of its 5 skills, 7 agents, 1 hook.

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 import-summarizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/rdel-group/compound-knowledge-work/import-summarizer.svg)](https://agentmods.dev/skills/rdel-group/compound-knowledge-work/import-summarizer)
Your own site
<a href="https://agentmods.dev/skills/rdel-group/compound-knowledge-work/import-summarizer"><img src="https://agentmods.dev/badge/skills/rdel-group/compound-knowledge-work/import-summarizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,079 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00099 $0.01079
Opus 5 $0.00049 $0.00540
Sonnet 5 $0.00020 $0.00216
Haiku 4.5 $0.00010 $0.00108

Measured 4d ago against content hash 0ec88d61610c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

import-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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/convert_document.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/import-summarizer/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Import Summarizer

Convert and process reference materials into indexed, context-budget-friendly summaries. This is the gateway for all reference materials entering a CKW project.

When to Use

  • /ckw:new-project --from-prd needs to read a PRD document
  • /ckw:import-reference processes reference materials
  • Any agent needs to convert a non-markdown document to readable text

Document Conversion

Supported formats

Format How CKW converts it
.pdf Claude's native Read tool — read the file directly, no script. Claude extracts PDF text and layout natively, which is more reliable than any shell converter.
.docx scripts/convert_document.sh — pandoc → textutil (macOS) → python-docx
.pptx scripts/convert_document.sh — pandoc (needs pandoc ≥ 3.7, which reads PowerPoint natively)
.html / .htm scripts/convert_document.sh — pandoc → textutil (macOS)
.rtf scripts/convert_document.sh — textutil (macOS) → pandoc
.txt / .md Direct read — no conversion

Convert the document

Detect the file type from its extension (matched case-insensitively — Report.DOCX is fine):

  • .pdf — Do not run the script. Use Claude's Read tool on the file directly; it extracts text and layout natively. (Older docs referenced a PyPDF2 fallback and a python-pptx path — neither was ever implemented, and neither is needed.)
  • .txt / .md — Read directly.
  • .docx / .pptx / .html / .rtf — Run scripts/convert_document.sh <filepath> (path relative to this SKILL.md). The script picks the right converter per format, verifies the output is non-empty before reporting success, and prints a clear error (including the converter's own stderr) if conversion fails. If it reports that no converter is available, tell the user what to install.

The script now fails loudly on empty/garbled output rather than returning silent garbage (the old behaviour for PDF and PowerPoint via textutil). If conversion fails, surface the error and offer to have the user paste the content manually.

Read the full file on GitHub · 82 lines

Files

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.

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. 4d ago First seen · 82 lines · 99 tokens per session scan A 0ec88d61610c

Subscribe to this mod's changes

import-summarizer is a skill published in the GitHub repository RDEL-Group/compound-knowledge-work (9 stars, last pushed 1mo ago), licensed MIT. It adds 99 tokens to every session and 1,079 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 2026-08-31.

Related

Other skills, from other repositories