Claude Code and Codex plugins their authors filed under "workflow". All categories.
Unified 3D printing pipeline for Bambu Lab printers — design (OpenSCAD MCP), browse (MakerWorld), slice STL→3MF (OrcaSlicer-backed CLI), arrange multi-object plates, and printer control via Bambu MCP. Bundles a TypeScript slicing CLI with patched OrcaSlicer profile handling.
1 skill
Audit and improve CLAUDE.md / AGENTS.md instruction files against modern harness engineering principles: leanness, anti-staleness, discoverability, and failure-driven gotchas. Scores each file on a 100-point rubric, flags volatile data that will rot, detects fast-moving frameworks (Next.js, Tailwind, React 19) and recommends training-cutoff-honesty blocks, then applies targeted cut/point/add edits after approval.
1 skill
Sends macOS notifications when Claude Code or Codex CLI finishes a task or needs your attention.
hooks
Report this window's Claude Code activity to the orchestratinator floor.
hooks
Exports current session segment (since last compaction) with system-reminder stripping -- main conversation, subagent transcripts, sidechains, and debug logs in structured markdown.
hooks
Converges on ONE call instead of a menu of options. Two modes: a three-agent sequential loop for value-tradeoff decisions, and a Persona Panel of 3-5 parallel independent experts for domain-expertise decisions.
1 skill
Behavioral guidelines for building and explaining: Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution, Explain for Understanding
1 skill
Records every time a Claude Code session waits on a person for permission, or stops because an API error or a safeguard refusal ended its turn, in one JSON Lines file that watchers read.
hooks
Claude Code を使う際の個人的な作業スタイル（文体ガイド、判断ルール等）をスキルとして集約するプラグイン
1 skill
The automatic half of Sutra: the layered operating contract, rule cards, hidden-Unicode warnings, a compaction brief, a verify-before-stop nudge under strict, and the build-orchestrator workflow. Installs sutra as a dependency.
hooks
Idiomatic Rust guidance for agents: patterns, anti-patterns, resource gates and workflow.
1 skill
Babysit a GitHub pull request with the babysitter daemon: take each review comment, review, failed check and stale or conflicting branch one at a time, fix it, push and reply until the pull request can merge.
Agents for RPI workflow — orchestrator, planner, researcher, implementor, and reviewer — using VS Code memory to manage workflow tasks.
Harness-native ECC operator layer - 67 agents, 278 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 · 67 agents · 1 MCP server · hooks
Harness-native ECC operator layer - 67 agents, 278 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 · 67 agents · 1 MCP server · 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 — 38 agents, 156 skills, 72 legacy command shims, selective install profiles, and production-ready hooks for TDD, security scanning, code review, and continuous learning
183 skills · 79 commands · 47 agents · 6 MCP servers · hooks
Harness-native ECC operator layer - 67 agents, 271 skills, 92 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 · 1 MCP server
Lintel — 9-step cycle (SENSE→CAPTURE) + role-lifting + context-warming + specialized agents + compliance tiering + multi-CLI
193 skills · hooks
太陽スタイルのコピーライティング、動画制作、Deep Research、要件定義、13層防御システムを含む統合プラットフォーム
120 skills · 22 MCP servers
Skills, workflows, role subagents and hooks for spec-driven work.
140 skills · hooks
Get Shit Done — a structured planning/execution/verification workflow for Claude Code (/gsd:*), MCP-backed project state. Re-published here as a dependency of cairn so it installs automatically; upstream is jnuyens/gsd-plugin (tracking open-gsd/get-shit-done-redux). Installable on its own too.
87 skills · 33 agents · 1 MCP server · hooks
The Agent Firmware skill set for Claude Code without cloning the full template: durable memory, context controls, safe shipping, debugging, TDD, review, planning, frontend craft, and terse-mode workflows.
67 skills
Agents, commands, hooks, and skills for autonomous coding workflows (AFK + Ralph), codebase research, planning, and infra tooling (Jira, GitHub, Terraform, Obsidian).
46 skills · 11 agents · hooks
The workflow itself: brainstorm, auto, audit, review, ship, plus the prd.json sprint system and its hooks.
52 skills · 4 agents · hooks
The Agent Firmware skill set for Claude Code without cloning the full template: durable memory, context controls, safe shipping, debugging, TDD, review, planning, frontend craft, and terse-mode workflows.
57 skills
The Harness Firmware skill set for Claude Code without cloning the full template: project memory, context trimming, cross-vendor and multi-agent code review, CI repair, planning, long multi-round tasks, performance tuning, UI and visual design, writing, and terse replies.
56 skills · 1 MCP server
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
50 skills · 2 agents
Idea → viable product: venture lifecycle (V0–V6), session/mission machinery, four pillar gates, independent reviewer + chronicler agents, guardrail hooks, and a live owner status page.
3 skills · 28 commands · 20 agents · hooks
Orchestrated /work command with pre-computed action plans
27 skills · 23 agents · hooks