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/rootbr/rooted/reviewing-javanpx skills add rootbr/rooted --skill reviewing-javagit clone --depth 1 https://github.com/rootbr/rootedWhat 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 | $0.00152 | $0.05336 |
| Opus 5 | $0.00076 | $0.02668 |
| Sonnet 5 | $0.00030 | $0.01067 |
| Haiku 4.5 | $0.00015 | $0.00534 |
Grade A, and why
reviewing-java 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 yesterday.
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 — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Java Reviewer
You are a Code Review Agent. You review Java code and produce actionable, verified findings.
Load-bearing rule: every finding MUST cite concrete code from the diff. No diff anchor → no finding — only speculation. One false positive erodes trust in the entire review; maximize real findings, minimize noise.
The workflow has six phases — Scope, Context, Agent Selection, Execute, Verify, Report — preceded by a Resume check. Each phase builds on the previous one, and you confirm with the user at three key points so the review stays collaborative rather than fire-and-forget.
reviewing-java/
├── SKILL.md
└── agents/
├── performance-reviewer/{prompt.md, references/checklist.md}
├── concurrency-reviewer/{prompt.md, references/checklist.md}
├── security-reviewer/{prompt.md, references/checklist.md}
├── reliability-reviewer/{prompt.md, references/checklist.md}
├── maintainability-reviewer/{prompt.md, references/checklist.md}
├── project-specific-reviewer/{prompt.md, references/checklist.md}
└── verification-agent/prompt.md
Spawn prompts and reports persist under review/ at the repo root. Resume checkpoint for each agent: the presence of review/<agent>/report.md.
Runtime layout written under the target repo's review/ (per-agent folders are kept by default as an audit trail; cleanup is optional after the final two files land):
review/
├── state.md # scope + context + selection (end of Phase 3)
├── <agent>/prompt.md # exact spawn prompt passed to each agent
├── <agent>/report.md # findings written by the agent (resume checkpoint)
├── B<N>/{prompt,report}.md # subsystem agents (MEDIUM/LARGE only)
├── verification/{prompt,report}.md # Phase 5
├── java-review.md # Phase 6 deliverable
└── java-review-rejections.md # Phase 6 deliverable
<agent> is a specialist reviewer directory name — one of { security, performance, concurrency, reliability, maintainability, project-specific } — or a subsystem ID B<N>.
What ships with it
16 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.
- agents/concurrency-reviewer/prompt.md 5.2 KB
- agents/concurrency-reviewer/references/checklist.md 162 KB
- agents/concurrency-reviewer/references/java-concurrency-questions.md 30 KB
- agents/maintainability-reviewer/prompt.md 6.0 KB
- agents/maintainability-reviewer/references/checklist.md 63 KB
- agents/performance-reviewer/prompt.md 5.9 KB
- agents/performance-reviewer/references/checklist.md 54 KB
- agents/project-specific-reviewer/prompt.md 3.7 KB
- agents/project-specific-reviewer/references/checklist.md 46 KB
- agents/reliability-reviewer/prompt.md 4.9 KB
- agents/reliability-reviewer/references/checklist.md 59 KB
- agents/security-reviewer/prompt.md 4.8 KB
- agents/security-reviewer/references/checklist.md 74 KB
- agents/verification-agent/prompt.md 5.9 KB
- README.md 5.2 KB
- references/java-invariants-review-checklist.md 20 KB
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.
- yesterday First seen · 427 lines · 152 tokens per session scan A 86a3b1b11965
reviewing-java is a skill published in the GitHub repository rootbr/rooted (21 stars, last pushed 26d ago), licensed Apache-2.0. It adds 152 tokens to every session and 5,336 once invoked, about $0.0008 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…