Automated error detection, learning, and prevention for Claude Code. Captures errors, tracks fixes, and blocks known-bad patterns with learned suggestions.
★not rated 2 5mo agoA
tokens not measured
originalMIT
Claude Code plugin: Claude orchestrates, Executor (grok or codex) implements tasks in isolated git worktrees, codex reviews read-only, Claude judges/reworks/merges. Review is never bypassed — including Claude's own fallback code.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Plan, deploy, and audit cloud infrastructure from a single reproducible spec, backed by a registry of declarative components that compile to plain Terraform.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Build a complete, professional digital product end to end — discovery, architecture, secure backend, auth, payments, performance, accessibility, SEO, and deploy — not generic AI output. A router skill asks 2-3 questions (English or Spanish), then activates the right specialist across the whole build lifecycle.…
★not rated 2 26d agoA
tokens not measured
originalMIT
Mobile UI/UX design intelligence — WCAG validator with OKLCH auto-correct, cross-platform parity diff for Compose vs SwiftUI, and theory-of-design (Fitts / Hick / Gestalt) layout checks. Specialised for Jetpack Compose, Android XML, SwiftUI, and UIKit.
★not rated 2 2mo agoA
tokens not measured
originalMIT
A Stop-hook gate for Claude Code: the session cannot end until the latest plan has been reviewed and explicitly approved by OpenAI Codex via the codex CLI.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Generate sequence diagrams directly from natural language descriptions using Swimlanes.io syntax. Describe any workflow (authentication flows, API interactions, microservice communication, CI/CD pipelines) and get correctly formatted diagram code instantly. Supports solid, dashed, and bold arrows, conditional branches.
★not rated 2 6mo agoA
tokens not measured
originalMIT
Shape Up SDLC harness for Claude Code: shaping, intake, orient, scope-mapping, building (T0-verified, sandboxed, scope-contracted), evaluation and QA skills orchestrated by a tech-lead.
★not rated 2
changed todayA
tokens not measured
originalMIT
A harness for long-horizon Claude Code work: goals decomposed into loop-runnable phases, hooks that catch the bad session, verified iterations, and decisions that stay yours.
★not rated 2 29d agoA
tokens not measured
originalMIT
Generic, plugin-based PR review for GitHub, Azure DevOps, and GitLab. Reviews with parallel passes built from synced skill packs (stack-aware, zero built-in reviewers) in a single session (Copilot CLI or Claude Code), with optional Codex second opinion.
See your Claude Code spend in USD per project, per git branch, and over time (by day, week, month), computed locally by reading the session logs Claude Code already writes to /.claude/projects. Never touches API traffic. Zero key, zero prompts, zero latency.
★not rated 2 1mo agoA
tokens not measured
originalMIT