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

audit

01

RaNDoM6913/claude-code-superkit

Command

Run comprehensive parallel audit — dispatches specialized agents by scope (frontend, backend, infra, security).

not rated 2 1mo ago A 20 tokens MIT

commit

03

RaNDoM6913/claude-code-superkit

Command

Conventional commit helper — analyze changes, detect secrets, create well-formatted commit.

not rated 2 1mo ago A 16 tokens MIT

dev

04

RaNDoM6913/claude-code-superkit

Command

Full-stack development orchestrator — always-on, 16 phases (0–15): read-docs → understand → architect → pseudocode → plan → contract → validate → implement → evaluate → verify → test → goals → review → critic → document → report.

not rated 2 1mo ago A 0 tokens MIT

lint

06

RaNDoM6913/claude-code-superkit

Command

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

not rated 2 1mo ago A 21 tokens MIT

new-migration

08

RaNDoM6913/claude-code-superkit

Command

Scaffold a new database migration file pair (up + down) with auto-detection of migration tool and numbering.

not rated 2 1mo ago A 22 tokens MIT

pair

09

RaNDoM6913/claude-code-superkit

Command

AI pair programming — switch between Driver, Navigator, TDD, Review, and Debug modes.

not rated 2 1mo ago A 18 tokens MIT

review

10

RaNDoM6913/claude-code-superkit

Command

Unified review orchestrator — detect changes, dispatch reviewers, validate findings, optionally post GitHub inline comments.

not rated 2 1mo ago A 20 tokens MIT

security-scan

11

RaNDoM6913/claude-code-superkit

Command

Run AgentShield security scan on .claude/ configurations — detect secrets, permission issues, hook injection, MCP vulnerabilities.

not rated 2 1mo ago A 23 tokens MIT

superkit-init

13

RaNDoM6913/claude-code-superkit

Command

Intelligent project setup — scan codebase, generate filled documentation, configure rules with real paths.

not rated 2 1mo ago A 18 tokens MIT

test

14

RaNDoM6913/claude-code-superkit

Command

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

not rated 2 1mo ago A 20 tokens MIT

workflow

15

RaNDoM6913/claude-code-superkit

Command

Run a predefined workflow template — bugfix, hotfix, spike, refactor, dep-upgrade, security-audit.

not rated 2 1mo ago A 24 tokens MIT

run-admin

17

RaNDoM6913/claude-code-superkit

Command Claude Code

Start admin panel — modes: live (default), demo (no backend), final (strict live + seed data).

not rated 2 1mo ago A 0 tokens MIT

start

19

RaNDoM6913/claude-code-superkit

Command Claude Code

Start full local stack (Docker + backend + bots + frontends + named tunnel).

not rated 2 1mo ago A 17 tokens MIT

stop

22

RaNDoM6913/claude-code-superkit

Command Claude Code

Stop full local stack (services only, Docker stays running).

not rated 2 1mo ago A 12 tokens 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: