RaNDoM6913/claude-code-superkit

Production-tested agents (56), commands (16), hooks (42), skills (22), and rules (19) for Claude Code and Codex CLI. All agents on Opus 4.8 — every prompt hardened by Claude Fable 5.

2Stars on the repository
174Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

test-generator

73

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

Generate tests following project patterns — table-driven, edge cases, multi-stack aware.

not rated 2 1mo ago A 18 tokens original MIT

test-runner

74

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

Auto-detect and run project tests — supports Go, TypeScript, Python, Rust, and more.

not rated 2 1mo ago A 24 tokens original MIT

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

Three.js color pipeline — sRGB vs Linear, toneMapping (None/ACES/Reinhard), texture colorSpace, when to use NoToneMapping for UI textures. Activate when color issues arise with 3D textures or rendered colors look wrong.

not rated 2 1mo ago A 55 tokens original MIT

tree-generator

76

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

Generate project directory tree documentation — auto-detect structure, filter noise, output clean markdown trees.

not rated 2 1mo ago A 21 tokens original MIT

ts-reviewer

77

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

Review TypeScript/React code for type safety, hooks correctness, state management, and conventions.

not rated 2 1mo ago A 22 tokens original MIT

ui-design-reviewer

78

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

Anti-slop UI review — typography, color calibration, layout diversity, motion quality, interactive states. Activate when reviewing frontend components for design quality.

not rated 2 1mo ago A 34 tokens original MIT

ui-reviewer

79

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

UI/UX review — accessibility, semantic HTML, z-index, animations, responsive, design tokens.

not rated 2 1mo ago A 23 tokens original MIT

visual-reviewer

80

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

Visual QA — screenshot comparison before/after, UI consistency check, design system compliance scoring.

not rated 2 1mo ago A 21 tokens original MIT

writing-agents

81

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

How to write Codex reviewer skills — SKILL.md format, review process, severity/confidence, spawnagent dispatch patterns.

not rated 2 1mo ago B 28 tokens original MIT

writing-commands

82

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

How to write Codex user-invocable workflow skills — orchestrator pattern, argument parsing, tool mapping, and dispatch guidance.

not rated 2 1mo ago A 29 tokens original MIT

project-scanner

83

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

Project introspection — detect languages, frameworks, database, structure, scale, auth, CI/CD.

not rated 2 1mo ago A 23 tokens original MIT

writing-hooks

84

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

How to write Claude Code hooks — lifecycle events, exit codes, profiles, jq/node parsing, settings.json wiring, and testing.

not rated 2 1mo ago A 29 tokens original MIT

skillsmp-search

85

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

Search 500K+ agent skills on SkillsMP marketplace before writing new agents, commands, or skills. Use when creating new .claude/ components or looking for community solutions.

not rated 2 1mo ago A 40 tokens original MIT

gan-evaluator

86

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

Runs Playwright against gan-generator's output, scores against the plan's rubric, returns concrete failures. Step 3 of 3 in GAN harness — the adversarial verification step.

not rated 2 1mo ago A 39 tokens original MIT

gan-generator

87

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

Implements features against a gan-planner plan. Writes code + Playwright tests in lockstep, ensures anti-slop checklist is clean. Step 2 of 3 in GAN harness.

not rated 2 1mo ago A 40 tokens original MIT

gan-planner

88

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

Plans testable feature implementations with concrete acceptance criteria + Playwright-verifiable test scenarios for the GAN evaluator loop. Step 1 of 3 in GAN harness.

not rated 2 1mo ago A 35 tokens original MIT

admin-auth-guide

89

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

Admin authentication and authorization system reference — login flow, JWT, TOTP, sessions, RBAC.

not rated 2 1mo ago A 23 tokens original MIT

api-conventions

90

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

SocialApp API design conventions — REST patterns, error format, naming, middleware, request/response contracts.

not rated 2 1mo ago A 24 tokens original MIT

db-patterns

91

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

SocialApp database patterns — pgx usage, migrations, repository layer, transactions, common queries.

not rated 2 1mo ago A 22 tokens original MIT

frontend-patterns

92

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

SocialApp admin frontend patterns — mock/live API layer, page structure, components, types, hooks.

not rated 2 1mo ago A 23 tokens original MIT

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

SocialApp user frontend state management — TanStack Query, Zustand, IndexedDB persistence, cache invalidation, multi-account isolation.

not rated 2 1mo ago A 28 tokens original MIT

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

SocialApp pagination and filtering patterns — cursor-based SQL pagination, LIMIT+1 hasMore, TanStack infinite queries, admin table pagination, debounced search.

not rated 2 1mo ago A 35 tokens original MIT

tg-miniapp

96

RaNDoM6913/claude-code-superkit

Skill Claude CodeCodex

A collection of patterns for Telegram Mini Apps, which are web apps opened inside Telegram, including device safe areas, fixed elements, navigation buttons, sharing, and fullscreen behavior.

not rated 2 1mo ago A 47 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: