Claude Code and Codex plugins their authors filed under "workflow". All categories.
TDD workflow with 6 specialized agents for test-first development, red-green-refactor cycle, and comprehensive quality analysis
2 commands · 6 agents
Award-informed product experience skills for AI coding agents: complete UI states, interaction craft, supporting imagery, forms, polish passes, and anti-slop visual design. Complements Superpowers and Apptension SDLC so frontend work ships calm, original, and complete — not template-blank.
7 skills
流程评价与效率分析技能包 — 制度流程解构（policy-digest）、流程目标/风险/控制点/效率评价，ontology_framework 的应用化插件
6 skills
Build new functionality with Claude Code — TDD, automated dev with review, and multi-work-item orchestration
5 skills · 1 agent
End-of-session wrap-up: detects what changed, updates CLAUDE.md with gotchas only, runs tests, commits only this session's files (creating a repo with a secret check for new projects), and prints a short status report.
5 skills
Save an unfinished session to a handoffs/ Markdown file (handoff) and pick it back up in a fresh session, with drift checks against the current code (resume-handoff).
5 skills
Adversarial review and build loops between Claude and OpenAI Codex: codec-review has Codex critique a plan or codebase read-only while Claude judges and rewrites; codec-build hands a frozen spec to a second model to implement, then runs a bounded review-and-fix loop over the diff. Needs the Codex CLI and codex login; without them, an opt-in same-family mode uses a different Claude model as the critic (weaker, still independent). Windows and macOS (macOS untested).
5 skills
PRD and TECH_REQ generating commands that can be used pre-EPCC workflow
2 commands · 2 agents
Git workflow automation with conventional commits, branch naming, and pre-commit hooks
1 skill · 2 commands
Live operator dashboard for long autonomous anvil runs: claims, phases, lease countdowns, event feed, and stuck-state detection served as a local web page, plus an optional Claude Code statusline segment.
1 skill · 1 command
Reply style contract: be brief, number subjects, letter questions, delegate the work to background subagents, and end every reply with a status label.
1 skill · hooks
Intelligent orchestrator for Platonic Coding workflow. Auto-detects intent and project state, then routes to the right next step—brainstorm a design, initialize a project (scaffold or recover specs from existing code), formalize drafts into RFCs, refine specs, implement from guides with tests, or review code compliance. Artifacts live under the project-root `.platonic/` directory (analysis, drafts, specs, impl). Single entry point for the complete specification-driven development lifecycle, with BRAINSTORM mode built in.
1 skill
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Harness-native ECC operator layer - 61 agents, 246 skills, 76 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 76 commands · 61 agents · 6 MCP servers · hooks
The most comprehensive Claude Code plugin — 38 agents, 156 skills, 72 legacy command shims, selective install profiles, and production-ready hooks for TDD, security scanning, code review, and continuous learning
185 skills · 79 commands · 48 agents · 6 MCP servers · hooks
The most comprehensive Claude Code plugin — 48 agents, 182 skills, 68 legacy command shims, selective install profiles, and production-ready hooks for TDD, security scanning, code review, and continuous learning
184 skills · 68 commands · 48 agents · 6 MCP servers · hooks
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
175 skills · 89 commands · hooks
The most comprehensive Claude Code plugin — 14+ agents, 56+ skills, 33+ commands, and production-ready hooks for TDD, security scanning, code review, and continuous learning
109 skills · 57 commands · 25 agents · hooks
The disciplined dev lifecycle — implement issues, review PRs, sync releases, test E2E, manage sessions, stash secrets, and enforce manifest-driven tool-call hooks. Includes /evaluate-agent-skills (NVIDIA SkillSpector/SkillEvaluator wrappers). OpenCode stderr: better-toolkits-bootstrap /toolkits-initial-setup.
39 skills · 72 commands · 2 agents · hooks
Dev lifecycle orchestrator. Start with /make-no-mistakes:domain-driven-advisor — the canonical entry point that inspects your repo, asks a few plain-language questions, and routes you across the six-family audit engine (schema-drift, contract-drift, ddd, explicit-architecture, strangler, enforcement-hooks), then runs a premortem on the aggregated remediation plan. Also ships disciplined Linear issue execution with worktree isolation, PR review with Greptile gating, team release sync, E2E test generation/execution, test suite previewer, security pentesting, MoSCoW + RICE prioritization, cross-platform secret stash via OS-native GUI prompts (zenity / kdialog / osascript / Get-Credential), and session management. 38 commands, 12 auto-activating skills, 2 specialized agents.
12 skills · 39 commands · 2 agents · hooks
Generic agentic workflow loop for Claude Code and Codex — 10 commands: /flow:plan (--prd) → /flow:execute (--quick) → /flow:validate (--fast, --security, --a11y, --visual, --review, --scenario) → /flow:done, plus /flow:run (a plan as a goal, opt-in capped Stop hook), /flow:bug-rca, /flow:bug-fix, /flow:release (--changelog), /flow:record-ddr and /flow:init (--context, --map, --kgai). Role agents worker/spike/scout keep contexts small (skill context-budget). Project-agnostic via <project> placeholders + per-repo .ai/workflows.config.json. Use `maude init` to scaffold the .ai/ skeleton.
24 skills · 10 commands · 16 agents · hooks
GitHub Copilot CLI variant (generated from se-harness): agent roster, harness skills, goal-loop commands, bundled enforcement hooks. Install this one with `copilot plugin install` — see docs/setup-guide-copilot.md.
22 skills · 14 commands · 13 agents
Complete collection of agents, skills, hooks, commands, and rules evolved over 10+ months of intensive daily use
9 skills · 23 commands · 12 agents · hooks
Lauren Tan's pstack engineering skills ported to Claude Code (MIT). Optional companion to bstack: design exploration, subsystem walkthroughs, multi-model review, blast-radius proofs, verification skills, unslop, 24 principles.
40 skills
Portable QA workflows for Claude Code, Codex, and Hermes Agent with contextual tool recommendations, bounded execution, verifiable evidence, acceptance validation, and equivalent offline HTML/PDF reports; 29 skills and 10 Claude commands
29 skills · 10 commands
Complete collection of agents, skills, hooks, commands, and rules evolved over 10+ months of intensive daily use
12 skills · 14 commands · 9 agents · hooks
Claude Code plugin: interview/scan, recommend, bootstrap, goal loop with HITL gates, three-tier memory, sync, export. Install this one in Claude Code.
8 skills · 14 commands · 13 agents · hooks
DevOps com execução segura v1.0 — leitura livre, mutação sob confirmação por comando, destrutivo bloqueado por guard script; 19 skills (AWS, Kubernetes, Docker, Linux, Nginx, PostgreSQL, observabilidade, incidente, segurança, Proxmox, automação, performance, backup, Laravel, confiabilidade, FinOps, IA, documentação) e 4 subagentes
24 skills · 7 commands · 4 agents · 1 MCP server
Portable spec-driven development for Claude Code, Codex, Hermes and OpenCode with human-readable contracts, durable operational state, traceability, bounded autonomous correction, and isolated fleets.
17 skills · 17 commands
Skills do ciclo deltaspec: projeto-init, projeto-infra, descoberta, rodada-insumos, spec-feature, spec-review, guarding-doc-integrity, handoff, doc-entregavel, gerar-diagrama, modelo-dados, status-pmo, audit-workspace, git-guard, project-review-dotclaude, ticket-to-jira, pedido-insumos, lote-debitos, busca-falhas, inicio-de-sessao, replan-doc, criar-release, release, memoria e eu-tenho-tdah.
25 skills · hooks