Code review

17,399 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

radar-suite

577

Terryc21/radar-suite

Plugin Claude Code

Bundles 8 skills · 709 tokens together

Six-skill audit suite for iOS/Swift codebases: data models, UI paths, data round-trips, time bombs, visual quality, and capstone grading. As of v2.0 every finding is classified on a 3-axis framework (real bug / scatter / dead code) with mandatory coaching citations to patterns in the audited codebase.

not rated 20 10d ago A tokens not measured original Apache-2.0

codesage-tools

578

iliaal/codesage

Plugin Claude Code

Bundles 1 skill, 10 commands, 2 agents, 1 hook · 368 tokens together

Claude Code integration for CodeSage, a Rust-based code intelligence engine. Slash commands for onboarding (init + index + global MCP registration + git hooks + agent hint), reset, incremental reindex with model-mismatch cleanup, retrieval benchmarking, and a subagent-driven review workflow that fans out feature-slice.

not rated 20 changed today A tokens not measured original MIT

ai-maintainer-copilot

579

yuxiaoji30-lang/ai-maintainer-copilot-skill

Skill Codex

Use when maintaining open-source projects with AI assistance: issue triage, pull request review, release notes, maintainer automation, Codex for OSS application evidence, and privacy or safety guardrails for AI-assisted workflows.

not rated 20 2mo ago A 50 tokens original MIT

code-review

580

10xHub/Agentflow

Skill Claude CodeCodex

Perform thorough code reviews, identify bugs, suggest improvements, and explain code quality issues.

not rated 20 yesterday A 19 tokens original MIT

refactor

581

moco-ai/moco

Command Claude Code

A command that suggests ways to refactor code, meaning change its internal structure without changing its intended behavior.

not rated 20 7mo ago A 22 tokens original MIT

tower/agentic-data-engineering

Skill Claude Code

Review a Tower data app for reliability and production readiness. Scores 5 gradient dimensions (incremental strategy, error resilience, resource efficiency, observability, test coverage) + 6 pass/fail checks. Modes — DEV REVIEW (read-only), PROD READINESS (makes changes, absorbs adjust-endpoint), INCIDENT (root…

not rated 20 4mo ago A 89 tokens

cdiff

583

garrrikkotua/cdiff

Skill Claude Code

Open a browser-based diff viewer showing all current changes in a VS Code-style file tree with syntax-highlighted diffs. Live-reloads as files change. Use when the user wants to "see the diff", "show changes", "what did I change", or "open diff viewer".

not rated 20 5mo ago A 62 tokens original MIT

xdg/xdg-claude

Plugin Claude Code

Bundles 1 skill · 52 tokens together

Implement TODO.md items one checkbox at a time via isolated subagents, with adversarial verification, code review, human-in-the-loop checks, and per-subsection commits.

not rated 20 yesterday A tokens not measured original Apache-2.0

deep-review

586

ronnycoding/.claude

Command Claude Code

Run parallel specialized PR reviews (Opus 4.6 for security/architecture, Sonnet 4.6 for the rest).

not rated 20 2mo ago A 27 tokens

mneme

587

MnemeHQ/mneme

Plugin Claude Code

Bundles 1 skill, 4 commands, 3 hooks · 105 tokens together

Enforce architectural decisions and engineering standards before Claude Code writes changes.

not rated 20 +1 today A tokens not measured original MIT

codeseeker

588

jghiringhelli/codeseeker

Plugin Claude Code

Bundles 6 commands · 0 tokens together

CodeSeeker - Intelligent code understanding with semantic search, knowledge graphs, and auto-detected coding standards.

not rated 20 +1 26d ago A tokens not measured

handoff

589

Xsxdot/handoff

Skill Claude Code

A coordination skill for handing an implementation plan to a separate coding process or remote machine, then tracking its progress. It uses the handoff command-line tool and supports independent executors such as Claude, Codex, or OpenCode.

not rated 20 +1 changed 3d ago A SkillSpector: pass 216 tokens original Apache-2.0

ramble

590

l1veIn/rambledesk

Skill Claude CodeCodex

Run a human-feedback loop through RambleDesk. Hard trigger: when the user invokes /ramble, $ramble, [$ramble], or says to use RambleDesk/ramble feedback, create a RambleDesk request before answering the substance unless they explicitly say not to send one. Also use when real human judgment, review, approval, or…

not rated 20 today A SkillSpector: pass 81 tokens original MIT

github_read

591

ParendumOU/Nexora

Skill Claude CodeCodex

Read access: repos, issues, PRs, files, branches, workflows, runs.

not rated 20 6d ago A SkillSpector: warn 0 tokens original MIT

pr-overview

592

ArjenSchwarz/agentic-coding

Skill Claude CodeCodex

Pull a PR from GitHub, run parallel review agents (code reuse, quality, efficiency, spec adherence) in read-only mode, surface unresolved comments, and write a self-contained HTML overview page to the repo root. Use whenever the user wants a read-only summary of a PR before deciding what to do — phrases like "overview…

not rated 20 changed 3d ago A 111 tokens

code-refactor

593

ZeroPointRepo/CRHQ-PRDs

Skill Claude CodeCodex

Skill "code-refactor" from ZeroPointRepo/CRHQ-PRDs, covering code refactor skill, when to use this skill, the two modes, core principles and the seven phases (shared by both modes).

not rated 20 4mo ago A 0 tokens

grasp-review-pr

594

ashfordeOU/grasp

Command Claude Code

Full PR review with blast-radius, suggested questions, and surprising-connections check.

not rated 20 +3 today A 15 tokens

are-you-sure

595

nscTechArt/are-you-sure

Skill Claude CodeCodex

Challenge a proposed software-engineering or technical-project solution before adopting it.

not rated 20 changed 2d ago A 19 tokens original MIT

audit-first

596

bearded-illirian/trailmark

Skill Claude CodeCodex

Audit-before-fix protocol — first find all gaps across 7 planes, prioritize, pin the gap table, and only then fix. Principle: never touch code until the full picture of problems is understood. Gap table → approval → flow-first per gap → library-first → plan → code. Use when: task begins with looking for problems…

not rated 19 changed 4d ago A SkillSpector: warn 96 tokens original MIT

Git

597

dean0x/devflow

Agent Claude Code

Unified agent for all git/GitHub operations - issues, PR comments, tech debt, releases.

not rated 19 today A 21 tokens original MIT

anthony-chaudhary/dos-kernel

Skill Claude CodeCodex

Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's dos verify and dos commit-audit — never the agent's own narration.

not rated 19 today A SkillSpector: pass 61 tokens original MIT

assumptions

600

Teycir/Assumptions

Skill Claude CodeCodex

Generate an evidence-backed Assumptions ledger for a Git diff, feature, endpoint, worker, migration, or code path. Use when reviewing a change, asking what could break, preparing a release, finding edge cases, assessing deployment safety, analyzing retries or concurrency, or designing failure-focused tests.

not rated 19 1mo ago A 63 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: