By yagizdo
Run a full development lifecycle from brainstorming and spec refinement through planning, multi-agent code review, debugging, and PR creation, with session handover support for resuming work across Claude Code sessions.
Detects wasted effort in diffs: unnecessary files, dead code paths, redundancy with existing codebase utilities, over-engineered abstractions, and ceremony the framework already handles.
Adversarial 7-phase security auditor with multi-platform mobile coverage (Flutter, Kotlin/Android, Swift/iOS), prompt-vs-code awareness for LLM plugin contexts, and supply chain analysis across CI scripts and dependency resolution.
Evaluates structural integrity via context7-driven convention discovery, diff manifest-aware boundary analysis, and pattern compliance grounded in the project's actual codebase -- not abstract ideals.
Evaluates code changes for developer experience quality across discoverability, error messages, debugging experience, and automation-readiness for both human developers and AI agents.
Systematic path tracer that finds logic defects by tracing each changed function's inputs through branches to outputs -- verifying correctness at every step rather than scanning for known bug patterns.
Explore ideas, compare approaches, and produce a validated spec before planning. Use when the user describes what to build, asks how to approach something, proposes a new feature or design change, or needs to explore options before implementation.
CodeGraph-first code navigation with LSP and grep fallback. Provides agents with a reusable strategy for semantic code exploration -- codegraph tools when available, LSP goToDefinition/findReferences/documentSymbol otherwise, grep as last resort.
Generate a Conventional Commits message, commit, and optionally push to remote.
Scaffold a new Claude Code agent with smart defaults from a natural language description or interactive Q&A.
Generate or rewrite an AGENTS.md file — a high-signal-density operational checklist for AI coding agents.
External network access
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Quiver is a development lifecycle plugin for AI coding CLIs. Purpose-built skills for brainstorming, planning, execution, debugging, code review, and session handover, plus specialized agents for review and debugging.
A normal feature cycle chains these skills. Each one is self-contained and works on its own. Skip steps, reorder them, or use just the ones you need. If you hit a bug at any point, run /hypothesis-debugging to investigate it systematically.
/brainstorm: turn a vague idea into a validated spec by walking through clarifying questions and trade-off analysis on 2-3 design approaches./plan: research the codebase in parallel, then break the chosen approach into verifiable step-by-step tasks with exact file paths./work: execute the plan task-by-task with continuous testing, branch setup, and incremental commits./commit: generate a Conventional Commits message from staged changes and commit (optionally pushing)./create-pr: open a GitHub pull request with an auto-generated title and description from the branch diff./review: dispatch review agents to check code quality, security, and architecture, then synthesize findings into one report. Runs 5 agents by default; --deep for the full pipeline./handover: save an 8-section summary of the session so the next session resumes with full context.Installation differs by CLI.
/plugin marketplace add yagizdo/quiver
/plugin install quiver@yagizdo/quiver
Then try /brainstorm in any session.
/add-plugin quiver
Or browse cursor.com/marketplace and click "Add to Cursor".
cursor-agent CLI does not load plugin skills (IDE-only). Use Cursor IDE for skill-using workflows.WebFetch and WebSearch are unsupported on Cursor; the included context7 MCP covers documentation lookups.preCompact event may use a different JSON field name than Claude Code. Edit .cursor/hooks.json to log raw stdin to a file, trigger context compaction, and inspect the log for the actual field names.codex plugin marketplace add yagizdo/quiver
Then try /brainstorm in any session.
Stop event with a 10-minute cooldown. For on-demand handovers, use /handover directly.AskUserQuestion is polyfilled as numbered text prompts: reply with the option number.spawn_agent(worker) with the agent's persona prompt read from agents/. The /review skill dispatches 5 agents by default, or the full pipeline with --deep.claude -p for transcript summarization. If the claude CLI is not installed, the auto-save hook will silently skip (manual /handover still works).gemini extensions install quiver
Then try /brainstorm in any session.
ask_user is native on Gemini CLI: interactive prompts render with full fidelity.PreCompress event. Unlike Codex's Stop event, no cooldown guard is needed: PreCompress fires only before history compression.agents/ and executes them inline. The /review skill dispatches 5 agents by default, or the full pipeline with --deep.claude -p for transcript summarization. If the claude CLI is not installed, the auto-save hook will silently skip (manual /handover still works).git clone https://github.com/yagizdo/quiver.git /tmp/quiver
/tmp/quiver/setup-opencode.sh /path/to/your-project
This copies Quiver's agents, skills, commands, plugin, and config into your
project's .opencode/ directory. After setup, open your project with opencode.
Quiver provides 20 specialist agents (@agentname), 12 slash commands (/ tab),
and 19 skills. The plugin hooks into session compaction to preserve handover context.
Note: OpenCode has no plugin marketplace or install command. Use the
setup-opencode.shscript above. For updates, re-run the script.Other differences from Claude Code:
AskUserQuestioninteractive prompts are not available — commands present choices as numbered lists. Multi-agent orchestration uses OpenCode's@agentmention and Task tool instead of Claude Code'sAgenttool. PreCompact hooks don't fire — use/handovermanually at session boundaries.Windows: Requires
git config core.symlinks truebefore cloning (Developer Mode or group policy grant needed).
| Component | Count |
|---|---|
| Hooks | 1 |
| Skills | 19 |
| Agents | 20 |
npx claudepluginhub yagizdo/quiver --plugin quiverAccess thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Complete developer toolkit for Claude Code
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer