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.
git clone --depth 1 https://github.com/tufantunc/review-proWrote 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/plugins/tufantunc/review-pro/core)<a href="https://agentmods.dev/plugins/tufantunc/review-pro/core"><img src="https://agentmods.dev/badge/plugins/tufantunc/review-pro/core/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/tufantunc/review-pro/core"><img src="https://agentmods.dev/badge/plugins/tufantunc/review-pro/core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
review-pro 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 26d 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.
What it actually says
{
"name": "review-pro",
"version": "1.5.1",
"description": "Tiered AI code-review: triage -> relevant specialist reviewers -> synthesis. Built to catch what AI-written code actually ships with: code that ignores what the repository already knows, needless dependencies, over-engineering, hallucinated APIs. Invoke the `review-pro` skill on a branch or PR.",
"author": {
"name": "tufantunc",
"url": "https://github.com/tufantunc"
},
"homepage": "https://tufantunc.github.io/review-pro/",
"repository": "https://github.com/tufantunc/review-pro",
"license": "MIT",
"keywords": [
"code-review",
"ai-code-review",
"security",
"code-quality",
"subagents",
"skills"
]
}
What it installs
The manifest is a name and a version. 15 skills, 16 agents travel with it, and installing the plugin installs all of them — 1,482 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill review-pro-synthesize A 45 tokens
- Skill review-pro-triage A 57 tokens
- Skill security A 63 tokens
- Skill ai-antipatterns A 62 tokens
- Skill api-contract A 67 tokens
- Skill correctness A 64 tokens
- Skill craft A 59 tokens
- Skill review-pro-verify A 55 tokens
- Skill a11y A 62 tokens
- Skill backend A 54 tokens
- Skill db A 52 tokens
- Skill dry A 49 tokens
- Skill frontend A 52 tokens
- Skill performance A 57 tokens
- Skill review-pro B 56 tokens
- Agent ai-antipatterns-reviewer A 45 tokens
- Agent a11y-reviewer A 47 tokens
- Agent backend-reviewer A 33 tokens
- Agent craft-reviewer A 37 tokens
- Agent db-reviewer A 35 tokens
- Agent performance-reviewer A 32 tokens
- Agent security-reviewer A 32 tokens
- Agent tests-reviewer A 33 tokens
- Agent spec-reviewer A 43 tokens
- Agent review-pro-synthesize-subagent A 44 tokens
- Agent review-pro-triage-subagent A 47 tokens
- Agent review-pro-verify-subagent A 52 tokens
- Agent correctness-reviewer A 35 tokens
- Agent frontend-reviewer A 33 tokens
- Agent api-contract-reviewer A 39 tokens
- Agent dry-reviewer A 41 tokens
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.
- 26d ago Changed 026241a82121
- 1mo ago Changed b514d13d137e
- 1mo ago Changed c0eff53b33ea
- 1mo ago Changed fb2f0b66fc96
- 1mo ago First seen · 21 lines scan A 53ed6d4aa193
review-pro is a plugin published in the GitHub repository tufantunc/review-pro (5 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
logic-lens
Logic-first code review using semi-formal execution tracing. Surfaces behavioral bugs, type contract breaches, boundary blindspots, and interprocedural semantic mismatches — the logic errors that cause production incidents in syntax-clean code.
logic-lens
Logic-first code review using semi-formal execution tracing. Surfaces behavioral bugs, semantic errors, and runtime failures that linters miss.
harness-engineering-skills
Two Claude Code engineering skills bundled as one plugin: review-loop (cross-LLM iterative code review with Codex or Gemini as peer) and harness (cybernetics-based Planner→Generator→Evaluator→Retro orchestration for complex tasks).
audit-protocol
Audits a code change against a 54-phase failure taxonomy and reports what it did not check, not just what it found. Domain overlays run first and force critical-path treatment.
norma
Checks AI-written code against your rules as it is written, and keeps a record of what it found.
brooks-lint
AI code reviews grounded in twelve classic engineering books — decay risk diagnostics with book citations, severity labels, and six analysis modes (PR review, architecture audit, tech debt, test quality, health dashboard, full-sweep auto-fix).