Claude Code and Codex plugins their authors filed under "development". All categories.
GraphyLoop Workflow v3 for Claude Code: the /graphyloop:chadi-* commands, the agent squad, core workflow skills and the graphyloop MCP server (wave planner, persistent memory, secrets, preflight).
3 skills · 15 commands · 26 agents · 1 MCP server
Diagnose complexity, model a domain in types, compose total functions, keep effects at the edges, and refactor toward all of it
43 skills
Workflow skills, worker agents and the task-orchestration flow for substantial changes.
35 skills · 7 agents · hooks
Concise coding conventions, evidence-based verification workflows, and audits for security, readiness, accessibility, operations, data, APIs and repositories.
41 skills · hooks
Browser superpowers for AI coding agents: dev-server and reverse proxy with traffic logging, a deduped priority error inbox, 50+ frontend diagnostic functions, accessibility/performance/security/SEO/responsive/API/loading audits, visual-regression snapshots, replay testing, tunnels, and sketch/design modes
36 skills · 4 agents · hooks
Core Final Factory development tooling: delegation roles (implementor, implementor-sonnet, code-analyst, mech-executor, scout, Explore, build-verifier, deep-thinker, game-driver) plus the skills for deep thinking, determinism audits, driving the game, playtests, handoff/resume, and doc upkeep.
30 skills · 10 agents
Agent orchestration toolkit. 19 skills, 15 commands, 7 native subagents, file-based memory, native Claude Code hooks, and an opt-in review cadence with a lock over the rules that state it.
18 skills · 15 commands · 5 agents · hooks
Dart task management with adversarial cooperation loops and full dart-query MCP schema parity - DartQL batch operations, advanced filtering, task relationships, documents, time tracking, and automated task execution through quality verification pipelines. Requires @standardbeagle/[email protected]+ (dartai_loop_snapshot tool used by /dartai:start).
29 skills · 6 agents · hooks
Six-phase threads (GOAL, PLAN, GO, CHECK, SHIP, MASTER) run by the local ork CLI: each claim is re-run against the repository before it counts, and you get short decisions only when they matter.
21 skills · 8 commands · 6 agents
Describe a change and ac builds it: parallel research, slices routed to haiku, sonnet or opus by cost, an independent review, and an unattended mode that ends at a read-only gate. Adds a planner, a roadmap coordinator, a QA pass, authoring skills and gated, fail-open hooks.
19 skills · 13 agents · 1 MCP server · hooks
Flutter implementation specialist plugin with 26 specialized agents for planning (orchestrator + 7 planning subagents), execution (6 do-* helper agents), code generation, generative UI, E2E testing, debugging, verification, data persistence, platform integration, UX, releases, environment management, and interactive session support
1 skill · 5 commands · 26 agents
AI Development Orchestrator with 6-state bash FSM, Fast Mode, and 87% token reduction. Dispatches role-based agents, enforces quality gates, and maintains auditable evidence trails.
14 skills · 12 commands · 5 agents · hooks
Production-hardened Claude Code with safety hooks, multi-stack agents, and 9 commands/7 skills
11 skills · 9 commands · 4 agents · 1 MCP server · hooks · LSP
Opinionated, evidence-verified audits of TypeScript and React codebases: architecture, testing, security, dependencies, quality gates, and more, with a Repository Quality Score.
30 skills
Seven specialized agents, structured workflows, and quality guardrails. Install and start building — no configuration needed.
8 skills · 8 commands · 12 agents · hooks
Helps solutions consultants build Canvas Medical plugins through guided dialogue and automated workflows
13 skills · 11 commands · 3 agents · 1 MCP server · hooks
A multi-agent development pipeline with Clean Architecture, test-first implementation and parallel review gates: /intent-and-goal → /run-pipeline, the reviewer agents it hands off to, the convention skills they read from, and a refactoring catalog. Tuned for Kotlin, Android and TypeScript.
11 skills · 6 commands · 10 agents · hooks
Development workflow -- issue planning, implementation, PR creation, code review with specialized reviewers, and project conventions
21 skills · 6 agents · hooks
Autonomous build-verify-fix loop. Decomposes a spec into castings with pre-authored teammate prompts, validates them through an 11-dimension F0.9 gate (including F0.7 intent-carrier coverage), builds in parallel waves with server-side evidence re-execution and per-requirement-ID binding, runs up to 8 verification streams (TRACE, FLOW_TRACE, PROVE, RESEARCH_AUDIT, COVERAGE_DIFF, SIGHT, TEST/PROBE, TEST_OBSERVATIONS), grinds defects to zero, then assays the result with fresh-eyes verification. Brownfield runs consume a flow delta; greenfield and cosmetic runs use the end-state pipeline. Forge plans. Foundry builds.
4 skills · 7 commands · 15 agents · 1 MCP server · hooks
Spring development skills for Boot, Web, Data, transactions, security, messaging, Cloud, and Batch workflows.
26 skills · 1 agent
Especialista Fluig: datasets ECMA 5/Rhino, formulários, workflow, widgets, layouts, Style Guide, fluigcli, montagem de fluxo de processo a partir de spec (mcp-fluig), agentes executor/revisor e orquestrador de testes. Regras de cliente ficam no AGENTS.md do projeto.
21 skills · 6 agents
Personal Obsidian knowledge base skills and agents — vault bootstrap (init), vault maintenance, note processing, multimodal capture (voice/image/PDF/YouTube), vault triage, research ingestion, schema validation, safe refactoring, epistemic provenance, grounded Q&A, review, link suggestions, and Obsidian syntax reference
15 skills · 11 agents · hooks
SLOP (Simple Language Open Protocol) integration for MCP management. Migrate existing MCP setups, search and execute tools, manage resources, and orchestrate multiple MCP servers. Includes Dart MCP tool reference skills for reduced get_metadata calls.
23 skills · 2 agents · 1 MCP server
Comprehensive SpiceDB development toolkit for designing permission models, generating schemas, implementing authorization, testing, and migrating from other authorization systems (OpenFGA, Okta FGA, Oso Cloud) to SpiceDB
8 skills · 15 commands · 3 agents
hodanov の共通スキル・サブエージェント一式
15 skills · 9 agents · hooks
Engineering discipline pack: skill + 11 slash commands + 4 safety hooks. Keeps AI on-task on long tasks (TaskCreate-anchored scope, anti-drift braking, optional autonomous mode that blocks 'stop' until tasks complete), enforces end-to-end verification + multi-pass vulnerability scanning + condition-based codex review + project-CLAUDE.md pitfall writeback, and blocks irreversible bash commands via PreToolUse hook. Cross-CLI by design.
1 skill · 23 commands · hooks
Nano-sized framework with 7 specialized agents, 14 slash commands, and strict tool enforcement for optimal Claude Code usage
13 commands · 7 agents · 5 MCP servers
Plugin para desenvolvimento TOTVS Fluig — ciclo completo: design (brainstorm), scaffolding (widget/dataset/form/workflow), revisão estática + testes (review) e deploy (verify).
17 skills · 5 agents · 2 MCP servers · hooks
Autonomous build-verify-fix loop. Decomposes a spec into castings with pre-authored teammate prompts, validates them through an 11-dimension F0.9 gate (including F0.7 intent-carrier coverage), builds in parallel waves with server-side evidence re-execution and per-requirement-ID binding, runs up to 8 verification streams (TRACE, FLOW_TRACE, PROVE, RESEARCH_AUDIT, COVERAGE_DIFF, SIGHT, TEST/PROBE, TEST_OBSERVATIONS), grinds defects to zero, then assays the result with fresh-eyes verification. Brownfield runs consume a flow delta; greenfield and cosmetic runs use the end-state pipeline. Forge plans. Foundry builds.
4 skills · 6 commands · 15 agents
Coding workflows
25 skills