By shakestzd
Optimize Claude Code context flows using modular plans that reduce tokens by 95%, parallel workflows cutting costs by 81%, zero-transformation architecture, and quick research commands launching 3 parallel agents in 1-2 minutes for peak workflow performance.
Manage unified Contextune-HtmlGraph configuration
Track and optimize Claude Code usage with intelligent recommendations
Clean up completed worktrees and branches
Interactive configuration for Contextune features (output style, status bar, CLAUDE.md)
Design system architecture, APIs, and component interfaces with structured workflow
GitHub issue management specialist. Creates, updates, labels, links, and manages issues efficiently. Handles bulk operations and templating. Perfect for deterministic GitHub operations at 87% cost savings with Haiku 4.5.
Autonomous execution of independent development tasks in parallel. Handles complete workflow from issue creation to testing and deployment. Use for any task that can run independently - features, bug fixes, refactoring. Optimized for cost-efficiency with Haiku 4.5.
Benchmark and analyze parallel workflow performance. Measures timing, identifies bottlenecks, calculates speedup metrics (Amdahl's Law), generates cost comparisons, and provides optimization recommendations. Use for workflow performance analysis and cost optimization.
Autonomous test execution and reporting across multiple languages and frameworks. Runs tests, generates reports, creates GitHub issues for failures, tracks coverage, and performs benchmarking. Optimized for cost-efficiency with Haiku 4.5.
Expert git worktree management and troubleshooting. Handles worktree creation, cleanup, lock file resolution, and diagnostic operations. Use for worktree lifecycle management and troubleshooting.
Analyze and optimize parallel workflow performance. Use when users report slow parallel execution, want to improve speed, or need performance analysis. Activate for questions about bottlenecks, time savings, optimization opportunities, or benchmarking parallel workflows.
Efficiently research topics using parallel agents via Contextune's /ctx:research command. Use when users ask to research, investigate, find information about topics, compare options, or evaluate libraries/tools. Activate for questions like "research best X", "what's the best library for Y", or "investigate Z".
Systematic architecture analysis following Understand โ Research โ Specify โ Decompose โ Plan workflow. Use for system design, solution evaluation, build vs buy decisions, and task decomposition. Activate when users say "design", "architect", "break down", "best approach", or "should I build".
Expert-level git worktree troubleshooting, cleanup, and management. Use when users have worktree issues, conflicts, cleanup needs, or questions about git worktree commands. Activate for problems like stuck worktrees, locked files, orphaned branches, or worktree removal errors.
Git-powered state awareness - track file changes, session context, decisions, and work history. Query what happened in previous sessions and during current session. Auto-activates for state queries and before duplicating work.
Matches all tools
Hooks run on every tool call, not just specific ones
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.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Precision-Tuned Context Engineering for Claude Code
Optimize context flow with modular plans (95% fewer tokens), parallel workflows (81% cost reduction), and zero-transformation architecture. Contextune your workflows for peak performance!
Claude Code has 80+ plugins with hundreds of slash commands. You can't remember them all.
Before Contextune:
You: "I need to run tests"
Claude: "Sure! Running tests..."
[30 seconds later, writes custom test script]
After Contextune:
You: "I need to run tests"
Contextune: ๐ฏ Auto-executing /sc:test (85% confidence, keyword match, 0.02ms)
Claude: [Executes /sc:test automatically]
Complete context optimization with session duration tracking, usage monitoring, and smart tool routing
Contextune v0.9.0 introduces comprehensive context engineering features that maximize session duration and minimize costs.
Measure context preservation effectiveness:
# View session metrics
./scripts/view_session_metrics.sh
# Example output:
Session: session_1730000000
Started: 2025-10-26 21:00:00
First Compact: 2025-10-26 21:28:00
Duration: 28.0 minutes
Status: โ
Good context preservation
Thresholds:
Automatic cost optimization based on quota consumption:
Track usage:
/usage # Claude Code's usage command
/contextune:usage # Paste output to track in Contextune
Intelligent delegation of expensive operations:
Cost savings: 77-87% per delegated operation Context benefit: 3x longer sessions before compaction
81% cost reduction + 2x speedup with three-tier intelligence
Contextune v0.3.0 introduces cost-optimized Haiku agents that dramatically reduce parallel workflow costs while improving performance.
Before (All Sonnet):
5 parallel tasks: $1.40 per workflow
1,200 workflows/year: $1,680/year
After (Haiku Agents):
5 parallel tasks: $0.27 per workflow (81% cheaper!)
1,200 workflows/year: $328/year
Annual savings: $1,356 ๐ฐ
parallel-task-executor - Feature implementation ($0.04 vs $0.27)
Autonomous development task execution:
- Creates GitHub issue and worktree
- Implements features
- Runs tests
- Pushes code and reports
Cost per task: $0.04 (85% savings!)
worktree-manager - Git worktree lifecycle ($0.008 vs $0.06)
Expert worktree management:
- Create/remove worktrees
- Diagnose lock file issues
- Bulk cleanup operations
- Health checks
Cost per operation: $0.008 (87% savings!)
issue-orchestrator - GitHub operations ($0.01 vs $0.08)
GitHub issue management:
- Create/update/close issues
- Label management
- Link to PRs
- Bulk operations
Cost per operation: $0.01 (87% savings!)
test-runner - Autonomous testing ($0.02 vs $0.15)
Multi-language test execution:
- Run tests (Python, JS, Rust, Go)
- Generate reports
- Create issues for failures
- Track coverage
Cost per run: $0.02 (87% savings!)
performance-analyzer - Workflow optimization ($0.015 vs $0.12)
Performance and cost analysis:
- Benchmark workflows
- Identify bottlenecks
- Calculate ROI
- Generate reports
Local-first observability and coordination platform for AI-assisted development. Go binary hooks for near-zero cold start.
Unified observability and orchestration for AI coding agents - yoking agents together
Quarto-based academic manuscript pipeline for journal submission. Scaffolds projects, builds publication-ready tables, detects AI writing tells, and generates upload packages. Agents: ai-tell-fixer, manuscript-reviewer, table-builder. Skills: manuscript-setup, build-upload, journal-compliance.
Research and publication pipeline โ 14 agents, 13 skills, 5 commands covering data extraction, analysis, visualization, writing, peer review, and journal submission. Integrates flowmpl (design system), quartopress (manuscript pipeline), prs-dataviz (medical figures), parameterized-manuscript pattern, and a full research toolkit.
CRISPI plan authoring and review in a local marimo notebook. /plan creates or reopens a structured YAML plan; human approvals persist to .moplan/moplan.db on every click.
npx claudepluginhub joshuarweaver/cascade-code-general-misc-2 --plugin shakestzd-contextuneHarness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Complete developer toolkit for Claude Code
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.