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/pr-reviewnpx skills add apache/tika --skill pr-reviewgit 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 | $0.00108 | $0.03720 |
| Opus 5 | $0.00054 | $0.01860 |
| Sonnet 5 | $0.00022 | $0.00744 |
| Haiku 4.5 | $0.00011 | $0.00372 |
Grade A, and why
pr-review 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local override: $TIKA_SKILLS_LOCAL/pr-review/LOCAL.md (default ~/.tika-skills),
read after this file, wins on conflict.
PR Review
Pre-flight: self-review before submitting
No PR number, no gh; scope is main...HEAD plus uncommitted. Inline, no
fan-out: walk dimensions 2 and 3 over every touched file, then §4 hygiene in
full (it is mechanical and it is what costs a review round-trip). Fix what
you find, then submit — no report to paste. Opt into the full path only for
a large or API-changing change.
1. Resolve scope
- PR number →
gh pr view <N> --json headRefName,baseRefName(read-only); diff isgit diff <base>...<head>. - Branch → diff against
main. No argument →main...HEAD+ uncommitted.
Resolve the merge-base to a SHA once (git merge-base <base> <head>); a
symbolic base drifts if anything fetches mid-review. Record it in the report.
The diff is the scope. Locate intent first — JIRA ticket, docs/, design
docs in commit messages — and collect prior punt lists or accepted residuals
(earlier review commits, PR discussion): those are settled; re-reporting them
wastes time. Ask the user only for constraints no document answers; forward
constraints learned mid-review to running agents.
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 · 298 lines · 108 tokens per session scan A 23f46a52f459
pr-review is a skill published in the GitHub repository apache/tika (4,028 stars, last pushed today), licensed Apache-2.0. It adds 108 tokens to every session and 3,720 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 2026-08-30.
Other skills, from other repositories
connector-review
Review an OpenMetadata connector against golden standards. Runs multi-agent analysis covering architecture, code quality, type safety, testing, and performance. When a PR number is given, automatically posts the quality summary to the PR description and a detailed review as a PR comment.
connector-audit
Deep reliability audit for OpenMetadata connectors — runs 7 investigation prompts (metadata, errors, auth, lineage, scale, synthesis, implementation) against connector standards.
playwright-validation
Use when validating UI changes in a branch require Playwright E2E testing. Reviews branch changes, validates UI with Playwright MCP, and adds missing test cases.
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.
test-locally
Build and deploy a full local OpenMetadata stack with Docker to test your connector in the UI. Handles code generation, build optimization, health checks, and guided testing.
ui-checkstyle
Run the exact ESLint + Prettier + organize-imports sequence that CI's UI Checkstyle workflow runs — on just the files the PR changed — and fail the task if any file ends up with a diff. Invoke after authoring or modifying any .ts, .tsx, .js, .jsx, or .json file under openmetadata-ui/src/main/resources/ui/src/…