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 agentmods add skills/apache/tika/file-to-markdownnpx skills add apache/tika --skill file-to-markdowngit clone --depth 1 https://github.com/apache/tikaWrote 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/apache/tika/file-to-markdown)<a href="https://agentmods.dev/skills/apache/tika/file-to-markdown"><img src="https://agentmods.dev/badge/skills/apache/tika/file-to-markdown.svg" alt="Measured on agentmods" 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 | $0.00147 | $0.04030 |
| Opus 5 | $0.00073 | $0.02015 |
| Sonnet 5 | $0.00029 | $0.00806 |
| Haiku 4.5 | $0.00015 | $0.00403 |
Grade A, and why
file-to-markdown scanned grade A with 1 finding 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.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
the tika-app CLI (zero setup, one file) or a running tika-server (curl, How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local override: $TIKA_SKILLS_LOCAL/file-to-markdown/LOCAL.md (default ~/.tika-skills),
read after this file, wins on conflict.
Using Apache Tika from an agent
Apache Tika turns almost any document into text you can read, and reports
per-document content as Markdown by default (4.x) — the format you
actually want, not raw XML or a wall of HTML tags. See below for why to
reach for the structured rmeta view rather than a flat blob, even when the
file looks simple.
This skill is for reading files, one at a time, inside your normal working loop. It is not a batch pipeline — see Batch processing, below, for why.
When NOT to reach for Tika: if your host can already read the file
natively (many agent environments read PDFs and images directly) and you
only need its visible text, use that — it's one step, not three. Tika earns
its place for everything else: .docx/.xlsx/.pptx, email (.eml,
.msg) and its attachments, archives, embedded content inside anything,
metadata (authors, dates, edit history), OCR, and the long tail of ~1000
formats nothing else opens.
Requirements: Tika 4.x needs Java 17+ (java -version to check).
No Java 17? In order of least pain:
-
Docker installed? Use the Docker route — zero local Java (see the
file-to-markdown-dockercompanion skill, ordocker run apache/tika:latest-full). -
No Docker either? Offer to install a user-local Java — ask the user first; never install software silently. The least invasive option is a Temurin JRE unpacked into a directory the user owns: ~45 MB, no admin rights, no PATH changes, uninstall = delete the directory.
mkdir -p ~/tika-jre && cd ~/tika-jre curl -L "https://api.adoptium.net/v3/binary/latest/21/ga/linux/x64/jre/hotspot/normal/eclipse" | tar xz ~/tika-jre/*/bin/java -jar tika-app.jar --versionSwap
linux/x64in the URL formac|windowsandaarch64as needed (Windows: fetch the.zipvariant and unzip). If the user prefers a managed install, the system package works too (temurin-21-jrevia apt,brew install --cask temurin@21,winget install EclipseAdoptium.Temurin.21.JRE) — that needs admin rights and touches system state, so it's their call, not the default. This skill describes Tika 4.x; on a 3.x install the defaults differ (3.x outputs XHTML, not Markdown, and some flags changed) — checkjava -jar tika-app.jar --versionorcurl localhost:9998/versionif behavior doesn't match what's described here.
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.
- 4d ago First seen · 320 lines · 147 tokens per session scan A 5928ea1c123c
file-to-markdown is a skill published in the GitHub repository apache/tika (4,028 stars, last pushed yesterday), licensed Apache-2.0. It adds 147 tokens to every session and 4,030 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pdf-processing
Extract text from PDFs, fill forms, and merge documents.
literature
Load when extracting GEO accessions, dataset metadata, and downloadable references from a scientific paper (PDF / URL / DOI / PubMed ID / raw text) for downstream omics analysis. Skip when the dataset is already in hand; only routing a query (use orchestrator).
sdrf:knowledge
Use when the user asks about the SDRF format, column naming rules, ontology mappings, modification format, reserved words, label types, or any SDRF specification question, wants a plain-language explanation of a column/error/concept, or needs to find/verify/compare ontology terms and accessions for a column. Also…
sdrf:review
Use when the user wants a comprehensive quality review of an SDRF file, a PR review of an SDRF submission, a quality score assessment, or to improve/score an existing SDRF strictly against templates and specification rules (specificity, completeness, consistency; no speculative additions).
agenthub
Browse, create, and complete tasks on Clawsy AgentHub — a distributed task platform for AI agents. Create tasks from GitHub repos, PDF/DOCX/PPTX/audio URLs, or plain text. Use custom LLM validation, earn karma. Categories: content, data, research, creative.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…