claude

shakestzd-contextune

Precision context optimization for Claude Code reducing token usage by 95% with modular plans and parallel workflows. Achieves 81% cost reduction.

0 on GitHubby Shakes Dlaminiv0.9.2MITupdated 6 months agocode_general
/

Plugin shakestzd-contextune from marketplace cascade-code-general-misc-2 in joshuarweaver/cascade-code-general-misc-2. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (8)

  • copilot-delegate

    Delegate GitHub operations and research tasks to Copilot CLI to preserve Claude Code session limits. Automatically activates when detecting GitHub keywords (issue, PR, repo, commit) or research needs (compare, research, lookup, best practices). Offloads heavy operations to Copilot subprocess and ret

  • decision-tracker

    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.

  • ctx:worktree

    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.

  • ctx:help

    Help users discover Contextune capabilities and understand how to use natural language commands. Use when users ask about Contextune features, available commands, how to use the plugin, or what they can do. Activate for questions like "what can Contextune do?", "how do I use this?", "show me example

  • ctx:parallel-expert

    Expert guidance on parallel development workflows using git worktrees and multi-agent execution. Use when users mention parallel work, concurrent development, speeding up development, working on multiple features simultaneously, or scaling team productivity. Activate for questions about task decompo

  • ctx:performance

    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.

  • ctx:researcher

    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 "inve

  • ctx:architect

    Systematic architecture analysis following Understand → Research → Specify → Decompose → 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".

Slash commands (14)

  • /shakestzd-contextune:contextune-config

    Manage unified Contextune-HtmlGraph configuration

  • /shakestzd-contextune:contextune-usage

    Track and optimize Claude Code usage with intelligent recommendations

  • /shakestzd-contextune:ctx-cleanup

    Clean up completed worktrees and branches

  • /shakestzd-contextune:ctx-configure

    Interactive configuration for Contextune features (output style, status bar, CLAUDE.md)

  • /shakestzd-contextune:ctx-design

    Design system architecture, APIs, and component interfaces with structured workflow

  • /shakestzd-contextune:ctx-execute

    Execute plan in parallel using git worktrees and multiple Claude sessions

  • /shakestzd-contextune:ctx-git-commit

    Deterministic commit and push workflow using scripts (DRY compliant)

  • /shakestzd-contextune:ctx-help

    Example-first command reference and quick start guide

  • /shakestzd-contextune:ctx-plan

    Document a development plan for parallel execution (modular YAML)

  • /shakestzd-contextune:ctx-research

    Fast research using 3 parallel Haiku agents for technical questions and decision-making (1-2 min)

  • /shakestzd-contextune:ctx-stats

    View Contextune detection statistics

  • /shakestzd-contextune:ctx-status

    Check status of parallel worktrees and tasks

  • /shakestzd-contextune:ctx-usage

    Track and optimize context usage with intelligent recommendations

  • /shakestzd-contextune:ctx-verify

    Verify and execute detected slash command with user confirmation

Subagents (5)

  • agent:issue-orchestrator

    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.

  • agent:parallel-task-executor

    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.

  • agent:performance-analyzer

    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.

  • agent:test-runner

    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.

  • agent:worktree-manager

    Expert git worktree management and troubleshooting. Handles worktree creation, cleanup, lock file resolution, and diagnostic operations. Use for worktree lifecycle management and troubleshooting.

MCP servers (1)

  • chrome-devtools

    runs: npx -y chrome-devtools-mcp

Hooks (16)

  • SessionStart

    uv run ${CLAUDE_PLUGIN_ROOT}/hooks/session_start_git_context.py

  • SessionStart

    node ${CLAUDE_PLUGIN_ROOT}/hooks/context_restorer.js

  • SessionStart

    node ${CLAUDE_PLUGIN_ROOT}/hooks/session_start.js

  • SessionStart

    node ${CLAUDE_PLUGIN_ROOT}/hooks/version_checker.js

  • UserPromptSubmit

    node ${CLAUDE_PLUGIN_ROOT}/hooks/context_injector.js

  • UserPromptSubmit

    uv run ${CLAUDE_PLUGIN_ROOT}/hooks/user_prompt_submit.py

  • PreToolUse

    uv run ${CLAUDE_PLUGIN_ROOT}/hooks/pre_tool_use_state_sync.py

  • PreToolUse

    uv run ${CLAUDE_PLUGIN_ROOT}/hooks/pre_tool_use_git_advisor.py

  • PreToolUse

    uv run ${CLAUDE_PLUGIN_ROOT}/hooks/tool_router.py

  • PostToolUse

    uv run ${CLAUDE_PLUGIN_ROOT}/hooks/contextune_plan_tracker.py

  • PostToolUse

    uv run ${CLAUDE_PLUGIN_ROOT}/hooks/contextune_execute_tracker.py

  • PostToolUse

    uv run ${CLAUDE_PLUGIN_ROOT}/hooks/tool_cost_tracker.py

  • PreCompact

    uv run ${CLAUDE_PLUGIN_ROOT}/hooks/context_preserver.py

  • PreCompact

    node ${CLAUDE_PLUGIN_ROOT}/hooks/compact_start.js

  • SessionEnd

    uv run ${CLAUDE_PLUGIN_ROOT}/hooks/session_end_recorder.py

  • SessionEnd

    uv run ${CLAUDE_PLUGIN_ROOT}/hooks/session_end_extractor.py

View source on GitHub

More from joshuarweaver/cascade-code-general-misc-2

All 149 plugins →

Analyzes Claude code repositories to extract patterns, dependencies, and architectural insights. Useful for developers conducting codebase audits and understanding project structure.

200 skills · 94 commands · 68 agents · 1 MCP server · hooks

0

Massive 225+ skill collection (613 Python tools, 32 agents) for Claude Code and coding assistants. Covers web development, data, automation, and agent patterns.

200 skills · 5 agents

0

A collection of reusable Claude commands and utilities for automating common tasks and workflows.

200 skills

0

Skill pack for Unity game development. Provides guidance and tools for building games and interactive 3D applications with the Unity engine.

200 skills

0

Similar plugins

MetaHarness integration — surfaces score/genome/mint/mcp-scan/threat-model via skills; pairs with @metaharness/router (ADR-148/149) for cost-optimal model routing; honors ADR-150 optional-augmentation constraint

13 skills · 1 command · 1 agent · hooks

ruvnet/ruflo 81,589

aws-core

claudecodex

Build, deploy, and operate applications on AWS. Skills to author infrastructure-as-code, use core services, and complete common tasks.

27 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

Long-term semantic memory for Claude Code, powered by OpenViking

5 skills · 1 command · 1 MCP server · hooks

volcengine/OpenViking 42,126

Engineer an agent's forgetting, not just its remembering. Four deterministic stdlib scripts implement the four lenses of agent memory: a cost profiler that splits construction from query spend and reports cost per correct answer (construction energy exceeds total query energy across 300 queries in the Stanford characterization); an architecture picker that scores the four paradigm families — long-context, flat RAG, structure-augmented RAG, agentic — disqualifies on hard constraints, names the cost the winning choice makes you pay, and refuses to pick when the top two tie; a density auditor that classifies every record in a memory directory or JSONL export as FACT / SKILL / LOG / PROSE, finds near-duplicates, and flags stale wording; and a forgetting-policy linter that fails any design with no forgetting rule. Ships cs-memory-engineer agent, /cs-memory-engineering and /cs-forgetting-audit commands, 4 references, and a seven-question forcing worksheet.

1 skill · 2 commands · 1 agent

alirezarezvani/claude-skills 29,725

Persistent project planning files with lifecycle hooks that inject selected plan context. Automatic recovery uses project files only. Explicit catchup modes may read same-project local session records to emit aggregate counts or bounded nonce-framed excerpts. Optional gated mode can request continuation on capable hosts and never runs commands declared in Markdown. No network upload path. Installs across 60+ agents.

6 skills · 13 commands · hooks

OthmanAdi/planning-with-files 28,031

gsd-core

claude

GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

72 skills · 72 commands · 64 agents · hooks

open-gsd/gsd-core 11,494

Maintain shakestzd-contextune?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins149 plugins