Apache Tika is a toolkit that reads many kinds of files and extracts their text and descriptive metadata, including from formats such as PDF, PowerPoint, and Excel. Applications and agent pipelines use it to turn documents into content they can process, search, or pass to language models. The catalogue skills provide reusable ways for coding agents to run Tika for file-to-Markdown extraction.
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/tika-eval-h2-querynpx skills add apache/tika --skill tika-eval-h2-querygit 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/tika-eval-h2-query)<a href="https://agentmods.dev/skills/apache/tika/tika-eval-h2-query"><img src="https://agentmods.dev/badge/skills/apache/tika/tika-eval-h2-query.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 | $0.00051 | $0.02189 |
| Opus 5 | $0.00026 | $0.01094 |
| Sonnet 5 | $0.00010 | $0.00438 |
| Haiku 4.5 | $0.00005 | $0.00219 |
Grade A, and why
tika-eval-h2-query 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 5d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local override: $TIKA_SKILLS_LOCAL/tika-eval-h2-query/LOCAL.md (default ~/.tika-skills),
read after this file, wins on conflict.
Query the tika-eval H2 database directly
tika-eval (Compare / Profile / Report) stores everything in an H2 database
— the -d <name> you pass to Compare produces <name>.mv.db. The xlsx/summary.md
reports only surface pre-canned views; for anything else (exact counts, custom
joins, "better vs worse" tallies the reports don't compute) connect to the H2 db
and run SQL.
Connecting (the part that trips people up)
tika-eval creates the db with no username and no password (H2Util calls
DriverManager.getConnection(url) with no creds). So:
- URL:
jdbc:h2:<absolute-path-without-the-.mv.db-suffix> - user / password: empty.
-user sa(H2's old default) fails with "Wrong user name or password" — the db wasn't created withsa. - Add
;IFEXISTS=TRUEso a typo opens nothing instead of silently creating a new empty db, and;ACCESS_MODE_DATA=rfor a safe read-only open. - H2 is single-writer: don't query while a
Compare/Profile/Reportrun has the db open (file lock). Query after the run finishes.
Use the h2-*.jar that ships with tika-eval-app (in its target/dependency/ or
the unzipped runtime lib/).
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.
- 5d ago First seen · 172 lines · 51 tokens per session scan A d776899279d8
tika-eval-h2-query is a skill published in the GitHub repository apache/tika (4,028 stars, last pushed 2d ago), licensed Apache-2.0. It adds 51 tokens to every session and 2,189 once invoked, about $0.0003 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.
Other skills, from other repositories
anyline
AnyLine数据库操作开发规范，涵盖动态数据源注册切换注销、DDL动态建表改表、DML增删改与事务管理、DQL动态查询与聚合统计、元数据管理、查询结果集的聚合、过滤、格式转换等数学计算，AnyLine方法内部会自动适配100+数据库方言，调用方法时忽略不同数据库差异。.
exasol-system-tables
Exasol system and statistics tables: what they contain, visibility prefixes (EXAALL, EXADBA, EXAUSER), and when to query them directly vs using MCP tools.
inspect-textdb
Load, query, and verify text-based databases (JSON/YAML files scattered across a directory tree, plus time-validity files) with the dbetto Python API: TextDB, AttrsDict, Catalog, Props, and the time utilities. Use this whenever someone points at a folder of JSON/YAML data or config and wants to read a value, walk the…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
connector-standards
Load all OpenMetadata connector development standards into context. Use before building or reviewing connectors to ensure consistent patterns.