Workflow plugins

Your Claude Code becomes Relay -- listens before proposing and helps choose the right approach.

Harness-native AIP operator layer - 68 agents, 290 skills, 94 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 · 94 commands · 68 agents · 1 MCP server · hooks

Harness-native ECC operator layer - 64 agents, 261 skills, 85 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 · 85 commands · 68 agents · 1 MCP server · hooks

Long-running coding-agent harness skills & workflows: intake routing, planning, per-component development, design, QA/review/security, and delivery.

200 skills

Semantic versioned releases with AI changelogs, worktree-aware

50 skills · 4 commands · 9 agents

Set the targets. Your agents do the rest. Say F[no] to mostly done.

28 skills · 1 command · 18 agents · hooks

Footnote nightly: yesterday's green main, rolling and replaceable.

28 skills · 1 command · 18 agents · hooks

Set a target and walk away. Say f[no] to mostly done.

27 skills · 1 command · 18 agents · hooks

Footnote nightly: yesterday's green main, rolling and replaceable.

27 skills · 1 command · 18 agents · hooks

TypeScript-first multi-agent team workflow harness — greenfield bootstrap, TDD, lightweight verification, deferred batched QA, branch guardrails, two-tier model routing, per-session run state, lifecycle-managed docs + LLM wiki, continuous learning, personal-brain pairing, ultracode orchestration

20 skills · 15 commands · 10 agents · 1 MCP server · hooks

Feature request to shipped work: intake, research, PRD and stories, UX design and audit, architecture with ADRs, implementation, root-cause debugging, code review, functional and UI QA — cycling until every gate passes.

3 skills · 14 commands · 23 agents

Lauren Tan's pstack engineering skills ported to Claude Code (MIT). Optional companion to deliver: design exploration, subsystem walkthroughs, multi-model review, blast-radius proofs, verification skills, unslop, 21 principles.

40 skills

Personal skills, commands, and workflows for Claude Code

31 skills · 7 agents

繁中台灣用語的九階段開發流程：/devwork（Claude Code）或 $bstack:devwork（Codex）啟動 brainstorm → plan → execute → verify → review → security → finish → pr-explain → retro

30 skills · 6 agents · 1 MCP server · hooks

Claude acts as a PM: discover, plan, get sign-off, decompose, and orchestrate build/review/ship via agents.

1 skill · 18 commands · 17 agents · hooks

High-accuracy skill activation (88%+) with AI-analyzed keywords, weighted scoring, synonym expansion, and three-tier confidence routing.

8 skills · 23 commands · 1 agent · hooks

Build a product with Claude as lead and parallel agents: waves, briefs, quality gate, releases, languages, What's new, polish, security and accessibility.

21 skills · 6 agents · hooks

Senior-engineer methodology skills and read-only subagents: architecture review, verification, test authoring, debugging, data migration, multi-session builds, agent security, and commit craft. Markdown only.

20 skills · 4 agents

Universal workflow skills for Claude Code — commit, ship, plan, debug, review. Stack-agnostic foundations that work with any project.

21 skills · 2 agents · hooks

Client-agnostic delivery process: ship-work-item ritual, GitHub-Issues backlog conventions, release ritual, retrospectives, versioning discipline, six team subagents, and an adopt-conventions scaffolding skill.

16 skills · 6 agents · hooks

Reusable planning, handoff, verification, and workflow skills for agents.

21 skills · hooks

Orka is a multi-agent engineering harness for Claude Code and Codex with resilient sprint scheduling, isolated implementation, bounded independent reviews, and mechanical merge-on-green.

8 skills · 6 commands · 6 agents · hooks

Generic plan-orchestration pipeline for Claude Code — walks any structured plan file to completion via scout/executer/verifier subagents with state persistence and per-Part review checkpoints.

1 skill · 8 commands · 5 agents

Stack-agnostic agentic dev workflow helpers: TDD, commits, PRDs, issue triage, pre-commit setup, design grilling, and a per-project config bootstrapper.

13 commands · hooks

Development workflow pipelines — clarify, feature-dev, team-feature-dev, bug-fix, cleanup, update-docs, autopilot.

10 skills · 3 agents

Autonomous development loop driven by GitHub or Gitea issues: spec → issues → batched builds → one CI run per batch → browser-verified deploy → user-viewpoint review.

7 skills · 5 agents · hooks

Curated review/build/test agents + secret-hardening/worktree/plan-gate hooks + supervise/wrap skills. Install once, use in every project.

6 skills · 1 command · 3 agents · hooks

3-role orchestration with strict phase isolation, auto-continuation, and security-hardened hooks

3 skills · 4 commands · 3 agents · hooks

Structured phase-gated workflow for software development and refactoring. Enforces deep analysis before implementation through six progressive phases, governed by a Software Architect.

10 skills · 1 command

Rarely used agent-harness skills (code-tour, harness-audit, harness-loop, loop, manager-audit, persona-review, reorg-sync, worker-setup, brain-ingest, writing-critique). Optional companion to agent-harness; install with /plugin install agent-harness-extras@agent.

10 skills · 1 agent