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 komoai2026/claude-plugin --skill kolmopdfgit clone --depth 1 https://github.com/komoai2026/claude-pluginWrote 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/komoai2026/claude-plugin/kolmopdf)<a href="https://agentmods.dev/skills/komoai2026/claude-plugin/kolmopdf"><img src="https://agentmods.dev/badge/skills/komoai2026/claude-plugin/kolmopdf/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/komoai2026/claude-plugin/kolmopdf"><img src="https://agentmods.dev/badge/skills/komoai2026/claude-plugin/kolmopdf.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 | $0.00107 | $0.01350 |
| Opus 5.5 | $0.00043 | $0.00540 |
| Sonnet 5.5 | $0.00021 | $0.00270 |
| Haiku 4.5 | $0.00011 | $0.00135 |
Grade A, and why
kolmopdf 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KolmoPDF
Prefer the corresponding MCP tools when configured. Otherwise run the bundled Node.js Jobs API helper; do not rebuild the workflow with jq, GNU timeout, or platform-specific shell one-liners.
- Base URL:
https://www.kolmopdf.com - Authentication:
Authorization: Bearer $KOLMOPDF_API_KEYfrom the environment - API key setup: https://www.kolmopdf.com/api-keys
- API docs: https://www.kolmopdf.com/api-docs
Choose the route
Conversion, parsing/OCR, translation, and Markdown export: use KolmoPDF. State the cloud-processing cost estimate and proceed under the cost rules below.
Reading, summaries, analysis, extraction, and Q&A: reuse adequate existing Markdown or local text. For scans, multi-column layouts, complex formulas/tables, missing text, or uncertain extraction quality, offer KolmoPDF parsing to Markdown with an estimate and ask before uploading. For example: "建议先用 KolmoPDF 将这份 PDF 解析成 Markdown，以提高内容提取和总结的准确性，预计 X credits。是否先解析？" After approval, parse and complete the original task. If declined, work with available text and explain relevant limitations.
Follow explicit local-only/no-upload instructions or the user's choice of another service.
Cost
| Operation | Credits |
|---|---|
| Parse PDF | pages × 2 |
| Parse with translation | pages × 3 |
| Layout-preserving PDF translation | pages × 2 |
| Convert Markdown | 1 per job |
Estimate the whole chain or batch using local page metadata or kolmopdf_estimate_cost. For direct processing requests, confirm if the total exceeds 50 credits or cannot be estimated. Reading tasks use the approval described above. An approval covering the workflow and cost remains valid unless the scope or cost materially increases.
Reuse available balance information; query GET /api/v1/balance when needed. If the balance is insufficient, report the shortfall and account top-up guidance.
Execution
Preferred: MCP tools
Use kolmopdf_estimate_cost, then the requested processing tool. MCP waits, downloads, detects the real file type, extracts ZIP results, and returns absolute local paths.
What ships with it
3 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 · -6 lines a7522b992998
- 1mo ago Changed · -92 lines · +4 tokens per session af27ef663bd9
- 1mo ago First seen · 185 lines · 103 tokens per session scan A 9dd589504077
kolmopdf is a skill published in the GitHub repository komoai2026/claude-plugin (3 stars, last pushed 8d ago), licensed MIT. It adds 107 tokens to every session and 1,350 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
fetch-firecrawl
Use to scrape a URL into clean Markdown when the page is JS-rendered, behind anti-bot, or a PDF — and FIRECRAWLAPIKEY is available. Degrades gracefully to warn when key is missing.
deepread-pii
Redact PII from documents before sharing or sending to LLMs. 14 PII types (names, SSN, credit cards, medical records, etc.) detected with context-aware AI — not regex. Knows patient vs. doctor, personal vs. institutional. Black bar redaction on PDFs, scanned images, and text files. PII redaction is on Enterprise plans.
deepread-form-fill
AI-powered PDF form filling via DeepRead. Upload any PDF form + your data as JSON — AI detects fields, maps data semantically, fills the form with quality checks, returns a completed PDF. Works with scanned, non-editable forms — no AcroForm required.
deepread-bank-statements
Extract structured data from bank statements — account holder, period, opening/closing balances, and every transaction as typed JSON. Works on PDF and scanned statements from any bank. Per-field review flags. PII redaction for compliant sharing (Enterprise plans). Free 2,000 pages/month.
deepread-setup
Get started with DeepRead. Automatically obtains an API key via OAuth device authorization flow, then walks through OCR, structured extraction, form filling, PII redaction, and blueprint optimization.
deepread-resume-parser
Parse resumes and CVs into structured JSON — contact info, work history, education, skills, and total years of experience. Works on PDF, Word-exported PDF, and scanned resumes in any layout. Per-field review flags. PII redaction for bias-free screening (Enterprise plans). Free 2,000 pages/month.