{"data":[{"slug":"governance-skill","title":"governance-skill","description":"Enforce engineering standards and code quality policies with zero-deferral code review. Finds and immediately fixes security issues, style violations, and standard breaches.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/wrsmith108/governance-claude-skill.git"},{"slug":"governance","title":"governance","description":"Engineering standards and code governance enforcement with parallel agent execution for code reviews, commits, and standards audits.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/wrsmith108/governance-claude-skill.git"},{"slug":"godot-prompter","title":"godot-prompter","description":"Agentic skills framework for Godot 4.x game development — 41 domain-specific skills that give AI coding agents deep expertise in GDScript and C#. Covers the full development lifecycle: project setup, architecture patterns, player controllers, animation, shaders, particles, audio, physics, 2D/3D rendering, UI, multiplayer, save/load, and deployment. Each skill provides tested code examples, comparison tables, common pitfalls, and implementation checklists. Includes 3 specialized agents for game architecture, implementation, and code review.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/jame581/GodotPrompter.git"},{"slug":"gemini-for-claude","title":"gemini-for-claude","description":"Bridge Claude Code to Google's Gemini CLI. Mirrors the pattern of the official Codex plugin but for Google's AI stack. Adds 9 slash commands under /gemini: for code review, adversarial security review with CVE search, web-grounded research via Google Search (capability Codex lacks), task delegation with 1M-token context, image generation via nanobanana, and background job management. Supports Google OAuth (free tier), API key, and Vertex AI auth. Zero npm dependencies — one auditable Node.js ESM companion script.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/philipvanlewis/gemini-for-claude.git"},{"slug":"g-cc","title":"g-cc","description":"Use Gemini CLI from Claude Code to review code and delegate tasks. Works via Gemini CLI subscription — no API keys needed. Includes code review, adversarial challenge review, task delegation with background jobs, and an optional review gate that checks Claude's output before stopping.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/spyrae/gemini-plugin-cc.git"},{"slug":"flow","title":"flow","description":"Flow turns Claude into a project partner who manages your backlog. Say \"park this for later,\" and it queues the idea. Say \"what's next?\" and it finds the highest-priority ready item and offers to start, handling the bookkeeping so you stay in flow.\n\nIt works as a lightweight scrum board with three ways to interact: talk to Claude conversationally, drag cards on the built-in Kanban board, or run multiple agents in parallel, each with filtered views. All three read and write the same backlog.json, no sync step, no drift.\n\nLanes are fully configurable. Start with the default agile flow (Backlog → Refined → Ready → In Progress → Code Review → Done) or define your own columns and gate rules. The board, the API, and the agent all enforce them consistently.\n\nConversational management: Add, reorder, refine, and complete items by talking naturally; no commands to memorize.\nBuilt-in Kanban board: Drag-and-drop web UI that syncs with the agent in real time; launch with one command.\nMulti-agent support: Leader agents assign work, worker agents get filtered views of only their items, plus unassigned ready work.\nAgent-initiated items: Claude adds bugs, tech debt, and follow-ups he discovers while working, linking them back to the source task.\nLinked items: Connect related items with typed links (blocks, follow-up, discovered-during, related) and a reason.\nConfigurable lanes: Define your own workflow columns and gate rules; the board, REST API, and agent all enforce them at every layer.\nThreaded refinement: Structured Q&A threads on items keep discussions organized; tag @Agent for async responses\nConcurrency safe: Optimistic versioning and atomic writes prevent data loss when board and agent write simultaneously","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/prajyotbankade/Flow.git"},{"slug":"eight-eyes","title":"eight-eyes","description":"Multi-agent code review with 8 hook-enforced roles. Each role targets a different failure surface — the skeptic reviews blind without the implementer's narrative, the security auditor can only run approved scan commands, the test writer cannot touch source code, and the implementer cannot run Bash. Scope boundaries are enforced through deterministic Python hooks at the PreToolUse layer, not through prompt instructions.\n\nThe 8 roles: implementer (scoped writes, no Bash), test-writer (test directories only), skeptic (blind read-only review), security auditor (read-only + approved scan commands), performance profiler (benchmarks in isolated worktree), accessibility checker (a11y tools + WCAG 2.1 checks), docs writer (doc paths only), and verifier (approved verification commands only).\n\nFeatures include parallel audit phase (4 review agents run concurrently), TDD mode (hook-level test-first enforcement), custom roles via manifest (--custom-role), REVIEW.md injection for project-specific review criteria, mission timeout and failure tracking.\n\n96 tests. 100% Python stdlib. Zero external dependencies.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/AgentBuildersApp/eight-eyes.git"},{"slug":"drillspark-workflow-toolkit","title":"drillspark-workflow-toolkit","description":"DrillSpark Workflow Toolkit is a Claude Code plugin for workflow analysis, Mermaid diagram validation, code review, test generation, and security review. It helps engineering, product, and operations teams use repeatable workflows for planning, reviewing, and improving implementation quality inside Claude Code.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/jackasser/drillspark-workflow-toolkit.git"},{"slug":"don-cheli-sdd-framework","title":"don-cheli-sdd-framework","description":"Full SDD (Spec-Driven Development) framework that turns requirements into tested, documented, production-ready code through 7 disciplined lifecycle phases. Includes 72+\n  slash commands (/dc:*), 14 reusable skills, 15 reasoning models, 4 estimation models, OWASP security audits, and adversarial code review. TDD enforced as an iron law.\n  Multilingual: Spanish, English, Portuguese.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/doncheli/don-cheli-sdd.git"},{"slug":"devflow","title":"devflow","description":"Structured AI development workflows for Claude Code. Enforces planning, approval, task tracking, and code review gates\nthrough MCP — so AI agents work within a defined process instead of writing code without oversight.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/KlausFreiberufler/devflow-mcp.git"},{"slug":"design-is-code-plugin","title":"design-is-code-plugin","description":"A UML-to-code methodology where tests force AI to follow your design. No code review needed.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/mossgreen/design-is-code-plugin.git"},{"slug":"delphi-dev","title":"delphi-dev","description":"Delphi development expert for Claude Code. Automatically applies Delphi Style Guide, Clean Code principles, and SOLID patterns. Includes technical audit (laudo técnico), code review, standardized code writing, and project scaffolding.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/adrianosantostreina/delphi-dev.git"},{"slug":"cto-toolkit","title":"cto-toolkit","description":"Complete CTO & Staff Engineer toolkit: 24 skills covering code review, architecture, DevOps, security, testing, and engineering management","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/camilooscargbaptista/cto-toolkit.git"},{"slug":"cortex","title":"cortex","description":"Cortex — SDLC Automation Engine by Alpha AI. Automates the entire software development lifecycle from idea to deployment. 37 slash commands, 11 specialized AI agents, and 9 auto-invoked skills covering project scaffolding, autonomous building, code review, testing, security scanning, CI/CD generation, and deployment. Supports Python/FastAPI, Node.js/NestJS, and Java/Spring Boot backends with Next.js frontend. Enforces production-grade standards: JWT auth, layered architecture, OWASP security, and performance best practices — all without human intervention.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/alphaaiservice/cortex.git"},{"slug":"coordinator-claude","title":"coordinator-claude","description":"Engineering management layer for Claude Code --- structures your session like a real dev team where you're PM and Claude is EM. Provides session workflows, multi-persona code review (staff engineer, UX, front-end, data science reviewers), structured planning, agent delegation, handoffs between sessions, and daily routines. You set direction; Claude makes engineering calls and runs them by you.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/oduffy-delphi/coordinator-claude.git"},{"slug":"codex-dispatch","title":"codex-dispatch","description":"Codex Dispatch is an agent skill for Claude Code that ensures every Codex MCP dispatch is correct. It enforces the right cwd (target repo, not workspace), sets approval-policy: \"never\" so Codex never blocks on prompts, picks the right sandbox mode for the task, and requires prompts to be fully self-contained. Covers code review, plan execution, and general repo tasks.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/jcardama/codex-dispatch.git"},{"slug":"codebase-quality","title":"codebase-quality","description":"Automated code review for codebase using multiple specialized agents.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/baranbingol1/claude-codebase-quality.git"},{"slug":"code-review-harness","title":"code-review-harness","description":"Code review skill using the Generator-Evaluator harness pattern. An independent Evaluator that actually runs the code to find bugs that code-reading alone misses.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"naokami3/ai_dotfiles"},{"slug":"closedloop","title":"closedloop","description":"Open-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learning — grounded in your codebase. Bootstrap, Plan, & Ship.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/closedloop-ai/claude-plugins.git"},{"slug":"claude-review-loop","title":"claude-review-loop","description":"Automated code review and swarm remediation for large changesets. Spawns adversarial reviewer agents, presents findings interactively, then dispatches fixer agents to remediate approved issues.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/andytango/claude-review-loop.git"},{"slug":"claude-library","title":"claude-library","description":"23 reusable skills, 2 agents, and smart hooks for any project. Covers the full development cycle: architecture mapping,\nimplementation planning, code review, safe refactoring, security-aware editing, quality audits, and 5 interactive learning\nmodules with persistent memory. Hooks auto-lint Python files, block destructive git commands, protect sensitive files, and\nauto-suggest relevant skills based on your prompt.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/tabers77/claude_experiments.git"},{"slug":"claude-flow","title":"claude-flow","description":"Structured project cognition + autonomous execution framework for Claude Code. Includes 9 skills (TDD enforcement, 8-layer\n  deep-task engine, persistent DAG scheduler, adversarial code review, bug diagnosis, feature planning, brainstorming), 3 specialized\n   agents (feature-builder, code-reviewer, test-writer), and 5 hooks (file protection, bash validation, lint feedback, session state\n  persistence, context reinjection). Helps Claude Code work on complex, multi-step engineering tasks with structure, verification,\n  and continuity.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/CookiRui/claude-flow.git"},{"slug":"claude-deep-review","title":"claude-deep-review","description":"A research-backed code review plugin for Claude Code that orchestrates parallel concern-specialized agents, cross-validates findings with deterministic verification, and produces unified review reports.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/liatrio-labs/claude-deep-review.git"},{"slug":"claude-codex-loop","title":"claude-codex-loop","description":"claude-codex-loop orchestrates a structured collaboration loop between Claude Code (designer/reviewer) and OpenAI Codex (auditor/implementer). It runs two stages — design and code — each with up to 5 rounds of iterative review plus an independent validation pass.\n\nHow it works:\n- Brainstorming (optional) — Explore requirements interactively before designing\n- Design stage — Claude Code writes a spec, Codex audits it independently each round until convergence\n- User gate — You review and approve the design before any code is written\n- Code stage — Codex implements, Claude Code reviews the full diff each round\n- Independent validation — A separate audit pass with zero prior context to catch groupthink\n\nAll work happens on a dedicated branch. Cancel anytime with /cancel-review to cleanly restore your starting state.\n\nCommands: /review-loop <task>, /cancel-review","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Whisker17/claude-codex-loop.git"},{"slug":"claude-code-kit","title":"claude-code-kit","description":"Turn any task into production-ready code. Specialized agents automatically handle planning, implementation, code review, and security scanning for any stack.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"This-HW/claude-code-kit"},{"slug":"claude-code-el-coderabbit","title":"claude-code-el-coderabbit","description":"CodeRabbit event source for the el plugin. Poll for new code reviews, comments, and thread replies on your pull requests as background events in Claude Code. When CodeRabbit posts a review or comment on a PR, it fires a task notification with the review details — letting your agent respond to code review feedback automatically. Supports thread reply detection for multi-turn review conversations. Requires the el event listener plugin and a GitHub repository with CodeRabbit enabled.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/mividtim/claude-code-el-coderabbit.git"},{"slug":"cassiiopeia","title":"cassiiopeia","description":"DevOps automation skills for full software development lifecycle. 20 skills covering code analysis, design, implementation, testing, code review, refactoring, documentation, troubleshooting, report generation,\nissue drafting, Git worktree management, Figma integration, and Spring Boot test generation. Supports Spring, Flutter, React, Next.js, Node.js, and Python projects. All skills output in Korean.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Cassiiopeia/SUH-DEVOPS-TEMPLATE.git"},{"slug":"byom-review","title":"byom-review","description":"Code review with any AI model via OpenRouter. Run standard and adversarial reviews against your working tree or branch using Claude, GPT,  Gemini, Llama, or any other model available on OpenRouter. Returns structured findings with severity, confidence, and actionable\nrecommendations. Includes cost tracking per review.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/jkrish/byom-code-review.git"},{"slug":"breezeware-dev-plugins","title":"breezeware-dev-plugins","description":"True Claude Code plugins for Breezeware development — auto-detecting, hook-powered, with skills and code review.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Breezeware-OS/breezeware-claude-plugins.git"},{"slug":"aurakit","title":"aurakit","description":"Sonnet Amplified fullstack development engine. Single /aura\ncommand activates 34 modes (BUILD, FIX, CLEAN, DEPLOY, REVIEW +\n28 extended). Features 5-step Sonnet Amplifier for Opus-level\ncode quality, SEC-01~15 OWASP-complete security rules, 13\nruntime hooks for zero-token enforcement, Tiered Model\n(ECO/PRO/MAX) with automatic model selection, 75% verified\ntoken reduction, 10 language-specific code reviewers, 5\nframework patterns, Instinct learning engine, and 8-language UI\nsupport.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/smorky850612/Aurakit.git"},{"slug":"audit-project","title":"audit-project","description":"Multi-agent iterative code review until zero issues remain. Spawns up to 10 specialist reviewers (code quality, security, performance, test coverage, architecture, database, API, frontend, backend, DevOps) chosen based on the project's signals. Each pass produces certainty-graded findings (HIGH / MEDIUM / LOW); HIGH findings auto-fix where safe. The orchestrator iterates passes until zero open issues remain or a max-iteration cap is reached. Specialists are role-based (defined inline via Task tool, not file-based agents) so they don't bloat the plugin's agent count. Designed to plug into /next-task and /prepare-delivery as the deep-review phase.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/agent-sh/audit-project.git"},{"slug":"attune-lite","title":"attune-lite","description":"Six developer workflow commands for Claude Code: code review, security audit, test generation, test fixing, bug prediction, and documentation generation.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/Smart-AI-Memory/attune-lite.git"},{"slug":"arcanum","title":"arcanum","description":"Advanced debugging, code review, deep research, technical documentation, creative ideation, and semi-autonomous development workflows with parallel theory validation, team-based research, war room investigation, root cause analysis, PR review assistance, elite technical writing, and Maestro development pipeline","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/burnsbert/claude-arcanum.git"},{"slug":"ai-devkit","title":"ai-devkit","description":"A structured software development toolkit that helps Claude Code follow senior-engineer workflows. AI DevKit provides phase-based development lifecycle (requirements, design review, planning, implementation, testing, code review), persistent memory for cross-session knowledge, test-driven development, structured debugging, code simplification, and technical writing review. It ensures consistent engineering standards across your projects with reusable skills and configurable workflows.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/codeaholicguy/ai-devkit.git"},{"slug":"ai-dev-kit","title":"ai-dev-kit","description":"AI Dev Kit is a complete plugin-oriented developer workspace for AI coding assistants. It ships everything needed to run professional-grade engineering workflows — TDD, code review, security audit, CI/CD, ML pipelines, infrastructure-as-code, code quality analysis, and debt tracking  across Claude Code, Codex, OpenCode, and Gemini CLI.\n\nThink of it as a system prompt that scales to 59 specialized skills and 33 domain agents, with lifecycle hooks and automated validation.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/noah-sheldon/ai-dev-kit.git"},{"slug":"agentops","title":"agentops","description":"Enterprise guardrails, delivery lifecycle, and self-evolution for Claude Code. Wraps every session in 7 security layers (path validation, command validation, injection scanning, credential redaction, exfiltration detection), structures work with the STAR methodology, and orchestrates full project builds from vision to merged PR through an 8.5-phase lifecycle with TDD enforcement, wave-based parallel execution, and two-stage code review. Includes 37 commands, 44 hooks, 12 specialist agents, 49 templates, and 32+ feature flags.","developer":null,"category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-10-13T18:00:00.395Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/garethdaine/agentops.git"}],"total":87,"page":2,"per_page":36,"observed_at":"2026-10-13T18:00:00.395Z","source_counts":{"web":342,"demo":13,"skills":5,"official":315,"community":2284,"knowledge-work":123}}