Composable development lifecycle -- brainstorm, plan, execute, review, and hand over from idea to merged PR
npx claudepluginhub yagizdo/quiverComposable development lifecycle -- brainstorm, plan, execute, review, and hand over from idea to merged PR
Session continuity, agent orchestration, and development workflows for Claude Code. Never lose context between sessions — carry your decisions, progress, and next steps forward automatically.
/plugin marketplace add yagizdo/quiver
/plugin install quiver@yagizdo/quiver
Then try your first command:
/handover
| Component | Count |
|---|---|
| Commands | 11 |
| Hooks | 1 |
| Skills | 5 |
| Agents | 6 |
| Command | Description |
|---|---|
/handover | Build an 8-section handover note with freshness checks and quality gates |
/load-handover | Load the most recent handover and highlight top priorities |
| Command | Description |
|---|---|
/delete-last-handover | Show and delete the most recent handover file with confirmation |
/delete-all-handovers | List all handover files, confirm, then delete everything |
| Command | Description |
|---|---|
/review | Multi-agent code review with synthesized findings |
Diff source (pick one):
/review # Review current branch (prompts for base)
/review --base main # Review against a specific base branch
/review <PR-URL> # Review a pull/merge request by URL
Output flags (combine with any diff source above):
--terminal # Print full report in terminal instead of saving
--output ./reports/ # Save report to a custom path (one-time)
--set-output ./reports/ # Save report to a custom path and remember it as default
--comment-pr # Post the review as a PR comment (opt-in)
Examples:
/review <PR-URL> --terminal # Review a PR and print in terminal
/review --base main --output ./tmp/ # Review against main, save to ./tmp/
/review --set-output ./reports/ # Set default save path for future reviews
/review <PR-URL> --comment-pr # Review a PR and post the report as a comment
When a PR URL is provided, you'll be prompted after the review to post it as a comment. Use
--comment-prto skip the prompt and post directly.
Re-review detection: If you run /review again on the same branch after fixing issues, it automatically detects the previous report and switches to re-review mode. It only flags new issues introduced since the last review -- no duplicate findings, no infinite review loops. If nothing functional changed, it approves immediately.
| Command | Description |
|---|---|
/commit | Generate a Conventional Commits message from staged changes, commit, and optionally push |
/commit # Commit with interactive prompt (commit, commit & push, edit, cancel)
/commit --push # Auto commit and push without prompting
| Command | Description |
|---|---|
/create-agent | Scaffold a new agent interactively from a description or Q&A walkthrough |
/create-agents-md | Analyze project context and generate an AGENTS.md checklist for AI agents |
| Command | Description |
|---|---|
/plan | Create a structured implementation plan with parallel agent research before coding |
/work | Execute a work plan or specification systematically with continuous testing and incremental commits |
| Command | Description |
|---|---|
/repair-skill | Diagnose and fix a broken skill by analyzing structure and verifying API references |
| Hook | Event | Description |
|---|---|---|
pre-compact-handover | PreCompact | Summarizes the conversation and saves a handover before Claude compacts context |
| Skill | Description |
|---|---|
orchestrate-agents | Discover agents, plan an optimal team, and coordinate parallel or sequential execution |
| Skill | Description |
|---|---|
create-agent | Agent authoring reference — frontmatter spec, category definitions, body structure, and quality gates |
Official prompts.chat marketplace - AI prompts, skills, and tools for Claude Code
Open Design — local-first design app exposed to coding agents over MCP. Install once with your agent's plugin command and projects/files/skills are reachable through stdio.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations