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-encoding-regressionnpx skills add apache/tika --skill tika-eval-encoding-regressiongit clone --depth 1 https://github.com/apache/tikaWhat 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 | $0.00060 | $0.02751 |
| Opus 5 | $0.00030 | $0.01375 |
| Sonnet 5 | $0.00012 | $0.00550 |
| Haiku 4.5 | $0.00006 | $0.00275 |
Grade A, and why
tika-eval-encoding-regression 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 2d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local override: $TIKA_SKILLS_LOCAL/tika-eval-encoding-regression/LOCAL.md (default ~/.tika-skills),
read after this file, wins on conflict.
tika-eval for encoding-detector regression hunts
A condensed pattern for finding SBCS→CJK style charset-detector regressions (or any "A picks encoding X, B picks encoding Y" question) without building two tika-app distributions.
Two configs, one build
Encoding-detector experiments don't need a "before" and "after" tika-app —
the chain composition is per-config. Run the SAME tika-app twice against
two configs, treat the outputs as -a and -b. Much faster than
tika-eval-compare's two-build flow.
# build once
./mvnw clean install -pl tika-app -am -Pfast -DskipTests \
-Dmaven.repo.local=$(pwd)/.local_m2_repo
unzip -q tika-app/target/tika-app-*.zip -d /tmp/tika-app-current
# two configs (any combination of detectors)
java -jar /tmp/tika-app-current/tika-app-*.jar \
--config=tika-config-3x-default.json \
-i <corpus> -o <workdir>/extracts/A -n 6
java -jar /tmp/tika-app-current/tika-app-*.jar \
--config=tika-config-junkfilter-combiner.json \
-i <corpus> -o <workdir>/extracts/B -n 6
# normal Compare
java -jar /tmp/tika-eval-current/tika-eval-app-*.jar Compare \
-a <workdir>/extracts/A -b <workdir>/extracts/B -d <workdir>/extracts/A-vs-B -r -rd <workdir>/extracts/A-vs-B-reports
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.
- 2d ago First seen · 231 lines · 60 tokens per session scan A b4fb98c32a84
tika-eval-encoding-regression is a skill published in the GitHub repository apache/tika (4,028 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 2,751 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
pr-checklist
Use when opening or finalizing a GitHub PR for OpenMetadata. Walks through the repo PR template — linked issue, high-level design (for big PRs), unit/integration/Playwright tests + coverage, UI screen recording, and manual test steps — then drafts a fully-filled PR body and (optionally) creates the PR.
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.
union-type-wrappers
Add typed getters and setters over BinaryData properties that represent TypeSpec union types in generated Java models. Use when generated classes expose BinaryData for union-typed fields and you need ergonomic, type-safe accessors instead.
run-tests
Run project tests using Maven (mvn). Use when the user asks to run tests.
search-m2
Search for Java classes inside Maven dependencies in /.m2. Use when the user asks to locate classes or inspect JARs. Cross-reference pom.xml files in the current directory to resolve dependency names/versions.