17,691 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.
Plugin Claude Code
The human-in-the-loop for AI coding: verify every turn against the real diff, then make the agent run/screenshot/test and self-fix before finishing.
stepanenkoviktor0110-boop/ai-dev-methodology
Skill Claude CodeCodex
A skill for resolving conflicting development requirements, where one part of a system is expected to satisfy opposing conditions. It looks for existing resources in the code and data structure, then tests possible ways to separate the conflict by structure, timing, conditions, or relationships.
Skill Claude CodeCodex
GitHub deep review: bugs, PRs, best fix, stale-or-real, read code first.
xinshixu7170/independent-critic
Agent Claude Code
Independently reviews a proposal / change / conclusion in a fresh subagent context. It does not inherit the conversation transcript, but it does receive the parent-written delegation prompt and the session's CLAUDE.md hierarchy, so it must verify claims against primary sources. 🔴 Main session: invoke it yourself…
Skill Claude CodeCodex
Use when authoring, editing, or reviewing a SKILL.md file — lints it against the Agent Skills best-practice rules and checks whether the description would actually activate the skill on the prompts it claims to cover, before the skill ships.
Skill Codex
Route explicit requests from a host coding agent to one or more locally configured AI executors through Codeck, attach Markdown or other project files, moderate cross-model consultation, expose disagreements, and synthesize traceable results. Use when the user explicitly names Codeck or asks to consult, compare, or…
Skill Claude CodeCodex
Review dashboard PRs needing your response and generate high-confidence update proposals for PRs where maintainers are waiting.
Skill Claude CodeCodex
Guides agents through a 7-phase rigorous feature development workflow with 4 independent cross-verification passes: systematic self-review, cold-context code review (reviewer sees no design docs — finds design-level blind spots single reviewers miss), behavior-preservation diff, and cross-repo impact scan. Use this…
Skill Claude CodeCodex
Create a PR on an OSAC component repo (including the osac mono-repo, which may need per-component validation for multiple touched components in one pass) using the fork-based workflow. Runs repo-specific validation (build, test, lint), pushes to the developer's push remote, and opens a PR against the upstream repo…
InstituteforDiseaseModeling/idm_standards
Plugin Claude Code
Bundles 10 skills · 982 tokens together
Audit and improve scientific research code and documentation against IDM engineering and documentation standards: code quality scoring, automated fixes, exhaustive per-file review, and docs audits.
Skill Claude CodeCodex
Create a standalone HTML artifact that presents a pull request for review. Shows before/after code changes, file-by-file tour with annotated diffs, risk map, review focus areas, and a short summary. Use when the user asks to write up a PR, summarize code changes visually, create a PR review document, show before and…
tianmind-studio/expert-review-panel
Skill Claude CodeCodex
A structured process for getting several role-specific reviewers to examine a paper, business plan, presentation, code, or other submission before it is sent out.
contrapuntal/antigravity-cli-plugin-cc
Plugin Claude Code
Bundles 4 commands, 1 agent · 91 tokens together
Use Antigravity from Claude Code to review code or delegate tasks.
Skill Claude CodeCodex
A code-review guide that checks readability, performance, security, design principles, and consistency with the existing codebase.
Skill Claude Code
This skill should be used when the user asks for a "code review", says "review this code", "review these changes", wants to "check for bugs", "look for issues", or asks for architectural feedback on code they've written.
Plugin Claude Code
Bundles 36 skills · 2,486 tokens together
Production-tested skills from Stone Giant Studio — artifact scoring, shutdown rituals, npm evaluation and security, CI/CD speedups, React Router v7, JavaScript/TypeScript, PostgreSQL/SQL Server/Drizzle/Kysely databases, testing, UI design, auth, AWS serverless, PDF generation, technical and marketing writing, product…
Skill Claude CodeCodex
Run a comprehensive code audit on any codebase. Analyzes security vulnerabilities, hardcoded secrets, dependency CVEs, test coverage, code structure, and AI-generated code patterns. Generates CODEAUDITREPORT.md with findings, severity ratings, and remediation guidance. Intelligently selects and orchestrates the best…
Skill Claude Code
Review code changes against a specification.
Skill Claude Code
Run a Claude–Codex adversarial review of a plan or code change. Use only when the user explicitly asks for a debate, cross-review, or second opinion; every round spends a paid turn on the other provider.
Skill Codex
Turn a pull request, branch, commit range, or working-tree diff into a standalone local HTML report that explains the actual outcome, architecture, flows, changed footprint, contracts, UI states, validation evidence, and selected implementation evidence. Use for understanding substantial completed changes, not for…
Skill Claude CodeCodex
Use when reviewing code, checking pull requests, identifying bugs, or suggesting improvements. Provides structured code review feedback.
Plugin Claude Code
Bundles 2 skills, 2 commands · 80 tokens together
OxLint, Biome, and Prettier configuration, linting skills, and pre-commit hooks for consistent code quality.
Cursor rule Cursor
CodeAnt AI code review and PR comment resolution integration.
Skill Claude Code
Open a REVIEW.md (written by /difit-review) in difit's browser UI for interactive review. Starts a difit instance (or pushes to one the user already has running on a given port), populates it with the unresolved threads from REVIEW.md. Optional — REVIEW.md is the source of truth; this skill just provides a nicer way…
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: