Deep Review Marketplace
- 5 repo stars
- Updated May 28, 2026
- Farfield-Dev/deep-review
deep-review is a Claude Code plugin that runs a five-phase adversarial code review with parallel sub-agents so developers receive a findings.md report with verified high-confidence issues.
About
deep-review is a Claude Code marketplace plugin packaging Farfield's production bug-finding recipe into a five-phase, parallel, adversarial repository review that emits findings.md. Reach for it on medium backends when you want a small set of high-confidence findings with severity and business impact categories instead of a long maybe-bug list. Expect roughly zero to ten findings on typical backends; static sites and pure UI repos surface less per the README limitations.
- Five-phase review with parallel sub-agents and adversarial validation
- /deep-review:run writes findings.md; artifacts live under ./.deep-review/
- --fast skips team-intent and product-scan phases for a cheaper pass
- Findings require impact categories and 100% confidence adversarial checks
Deep Review by the numbers
- Data as of Aug 10, 2026 (Skillselion catalog sync)
/plugin marketplace add Farfield-Dev/deep-reviewAdd your badge
Show developers this marketplace is listed on Skillselion. Paste this into your README.
| repo stars | ★ 5 |
|---|---|
| Last updated | May 28, 2026 |
| Repository | Farfield-Dev/deep-review ↗ |
How do you get a senior-engineer-grade, adversarially validated bug review of a repo without drowning in low-confidence noise?
Run /deep-review:run for a five-phase adversarial repo review that writes findings.md with severity, impact category, and verification artifacts.
Who is it for?
Developers reviewing medium backend codebases who want findings.md with severity, impact category, and verification artifacts.
Skip if: Static sites or pure UI repositories where the README says the review surfaces little, or teams wanting exhaustive bug counts.
What you get
findings.md at the repo root plus intermediate artifacts under ./.deep-review/ after adversarial validation.
Plugins in this marketplace
1 plugin - install individually after you add the marketplace.
Recommended Marketplaces
Beast Modeaaronstatic is a Claude Code marketplace for testing.6
Ai Skill Test Bddai-skill-test-bdd is a Claude Code marketplace for testing.
Ai Test Failure AnalyzerAI Test Failure Analyzer is a Claude Code plugin that diagnoses failing tests by gathering evidence from git history, logs, and config rather than guessing at fixes.
Android Test Pilotandroid-test-pilot is a Claude Code plugin marketplace from panicgit/android-test-pilot that automates Android app testing with a text-first strategy cheaper and faster than screenshot-per-step mobile-mcp loops.1
Anti Hallanti-hall is a Claude Code plugin marketplace centered on a single verify-first discipline plugin for developers who ship with agents daily.1
Askqa Marketplaceaskqa-marketplace is a Claude Code marketplace for testing.FAQ
What command runs the review?
/Deep Review:run in the repository you want reviewed per the README.
What does --fast do?
It skips team-intent and product-scan phases for a cheaper, faster, narrower review per the README.
Where is output written?
findings.md in the repo with intermediates under ./.Deep Review/, which you should gitignore.