Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By cosmicdreams
Team sprint execution infrastructure: agents, skills, hooks, protocols, and kanban pipeline.
npx claudepluginhub cosmicdreams/claude-plugins --plugin sprintFresh-eyes review of completed slice-worker output. Validates the fix independently — runs quality gates, checks for stubs and test theater, delivers APPROVED or REJECTED verdict with evidence.
Deep investigation, root cause analysis, and fix implementation for complex bugs that have defeated standard attempts. Spawned by team-lead on 3-fix escalation from slice-worker. Owns the card to completion.
Audits implementations against specs, validates claimed completions aren't stubs or shortcuts, and creates pragmatic plans to close gaps. Use when something is claimed done and needs verification.
End-to-end issue worker. Analyzes, implements, tests, and validates a single Drupal issue in one context window. Primary workhorse of the vertical slice pipeline.
Coordinates sprint team, assigns tasks, manages workflow. Only role that communicates with user in natural language.
Structured usage audit of sprint process assets -- agents, skills, hooks, and protocols. Analyzes session logs to classify each asset as actively-used, rarely-used, never-invoked, or trigger-failure. Use when running a deliberate asset audit, evaluating what to retire or merge, or when the user asks "audit sprint assets", "which skills are unused", "what agents are never spawned", "asset usage report". ON-DEMAND ONLY -- do not invoke as part of standard sprint workflow. Only the process-engineer agent or an explicit user request should trigger this.
Board-specific rules for the sprint Beads database (.beads/sprint.db). Use before creating, claiming, or interpreting any card in the sprint board. Provides lane definitions, card fields, DDEV slot rules, and agent role mappings. Trigger phrases include "create sprint card", "show sprint board", "sprint board columns", "add issue to sprint", "open sprint board", "launch sprint board". Always pair with sprint:kanban for universal kanban rules. Do NOT use for the retrospective-actions board -- use retro:kanban instead.
Universal kanban standards that apply to every board in this project. Use when creating a card, moving a card between lanes, querying card state, or understanding kanban conventions. This is required reading before touching any kanban board. Trigger phrases include "work a ticket", "advance a card", "update the board", "create a card", "kanban rules", "card format". After reading this, also read the board-specific skill (sprint:board for sprint, retro:kanban for retrospective-actions) for lane definitions. Do NOT use this as the sole reference for a specific board -- always pair with the board-specific skill.
Prepare an ordered, dependency-aware work queue and create Beads cards before launching a team sprint. Use when the user wants to plan a sprint, prioritize issues, sequence work by dependencies, order the backlog, or propose agent assignments. Trigger phrases include "plan a sprint", "which issues should we work on", "sequence these issues", "prioritize the backlog", "order the backlog by dependencies", "what order should we tackle these". This skill ONLY plans and creates cards — it does NOT execute agents or start work. Use sprint:run to actually execute the sprint after planning. Do NOT use for mid-sprint re-prioritization, retrospective planning, or when the user asks to start/run/work on issues immediately.
Synthesize completed sprint beads into a structured RELEASE-NOTES.md entry. Use when asked to "write release notes", "project release notes", "document completed cards", "summarize what we shipped", "what did the sprint accomplish", or "update RELEASE-NOTES.md". Reads closed beads from .beads/sprint.db and git log, drafts entries, confirms with team-lead, then prepends to analysis-reports/RELEASE-NOTES.md. Do NOT confuse with sprint:release-notes (changelog) which reads the plugin CHANGELOG.md version history -- this skill documents project-level sprint outcomes, not plugin versions.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
AI image generation Creative Director powered by Google Gemini Nano Banana models. Claude interprets intent, selects domain expertise, constructs optimized prompts, and orchestrates Gemini for best results.
Plugin, agent, and skill management tooling: bump-version, scaffold, new-agent, new-skill, optimize-agents, update-plugins, create-worktree.
Sprint retrospective infrastructure: agent interviews via SubagentStop hook, session analysis, action cards, and retrospective kanban board.
Pre-work ideation with a visual decision canvas. Generates divergent ideas, launches a local web UI for human annotation, then synthesizes decisions into a concrete plan.
Drupal-specific development skills and agents (DDEV, Analysis, Validation, Scaffolding).
Automated Drupal and WordPress error monitoring and self-healing pipeline: watches logs (DDEV + Acquia), triages errors into curated Beads tickets, autonomously implements fixes in isolated git worktrees, captures verified Actual solutions alongside Projected hypotheses, and surfaces past fixes via /drover:recall.
A collection of Claude Code plugins covering team sprint orchestration, Drupal development, process engineering, passive knowledge capture, and meta-tooling for plugin authoring.
Several plugins require external CLI tools (Beads, Obsidian CLI, GitHub CLI, jira-cli, ddev, etc.).
→ See DEPENDENCIES.md for the full install guide.
# Clone the repo
git clone git@github.com:cosmicdreams/claude-plugins.git
cd claude-plugins/worktrees/main
# Install plugins at user scope
claude plugin install admin@local --scope user
claude plugin install sprint@local --scope user
claude plugin install retro@local --scope user
claude plugin install ideate@local --scope user
claude plugin install drupal-lab@local --scope user
claude plugin install lib@local --scope user
claude plugin install workflow@local --scope user
claude plugin install drover@local --scope user
claude plugin install research-lab@local --scope user
claude plugin install improve@local --scope user
claude plugin install ideas-funnel@local --scope user
After installing, initialize the sprint board in your project:
brew install beads
bd init --prefix sprint
adminMeta-tooling for developing and maintaining Claude Code plugins.
Skills: agent-team, bump-version, changelog, create-worktree, install, new-agent, new-skill, optimize-agents, scaffold, scaffold-silence, update-plugins
sprintTeam sprint execution: parallel agents, kanban pipeline, hooks, protocols.
Skills: asset-audit, board, kanban, plan, project-notes, run
retroEnd-of-sprint retrospectives: agent interviews via SubagentStop hook, action card management, session reports.
Skills: interviews, kanban, session, transcript
ideatePre-work ideation: brainstorm canvas, deep research, structured comparison, reality checks, diagrams, ADRs.
Skills: adr, brainstorm, compare, diagram, reality-check, research, understand
drupal-labDrupal development against DDEV: issue analysis, patch validation, contrib module scaffolding, performance profiling.
Skills: analyze-issue, browse-drupal-issues, config, ddev, finish-issue, issue-summary, module-dev-starter, perf-measure, process-lifecycle, validate-patch
libThin CLI-wrapper skills (data-layer only — no summarization). Slack, Jira, GitHub, TestRail, Obsidian vault, logs, and media utilities.
Skills: archive, csv-analysis, ddev, ffmpeg, github, hyperfine, image-optimize, jira, lighthouse, log-analyzer, pa11y, slack, testrail, vault-search, vault-store, wiki-query
workflowProcess automation built on top of lib: morning brief, deploy checklist, cross-source pulse, Obsidian maintenance, calendar/email helpers.
Skills: config, deploy-post, ecosystem-pulse, morning-brief, obsidian-lint, organize, personal-calendar, personal-email, pulse
droverAutomated Drupal error monitoring and self-healing pipeline. Watches logs, triages errors into curated Beads tickets, autonomously implements fixes in isolated git worktrees, notifies on ready-for-review.
Skills: add-project, backfill, baseline, board, dashboard, implement, reset-state, run, setup, triage, watch
research-labComposable research engagement pipeline: literary review via NotebookLM, multi-agent workshop swarms, cross-examination seminars, and iterative experimentation with ratchet-based optimization.
Skills: experiment, literary-review, run, seminar, workshop
improveProcess engineering methodology. Maps process topology, makes directed fixes, runs improvement experiments, accumulates lint rules. Domain-agnostic — each plugin can own its own :improve skill for domain-specific knowledge.
Skills: accessibility-scan, attach, experiment, fix, lint, perf-measure, self
ideas-funnelPassive knowledge capture pipeline — Karpathy-derived LLM Wiki with Monitor-driven multi-domain ingest. Feeds land in Raw/, agents compile them into a cross-linked Obsidian wiki, memory evolves via confidence decay and graph-aware consolidation.
Skills: ingest, init, lint, query
admin:changelog <plugin> # e.g. admin:changelog sprint
admin:changelog <plugin> --latest # most recent version only
Chris Weber