ClaudeMod
Back to browse
Harnesses

Awesome Claude Code Toolkit

rohitg00's comprehensive toolkit of Claude Code resources — curated MCP servers, hooks patterns, agent templates, and deployment guides for production use.

Rohit Ghumare1,833 starsAdded 3 months ago

Claude Code Toolkit

The most comprehensive toolkit for Claude Code -- 135 agents, 35 curated skills (+400,000 via SkillKit), 42 commands, 176+ plugins, 20 hooks, 15 rules, 7 templates, 15 MCP configs, 26 companion apps, 53 ecosystem entries, and more.

rohitg00%2Fawesome-claude-code-toolkit | Trendshift

Awesome License: Apache-2.0 PRs Welcome Last Updated Files

Star History Chart

Quick Install

Plugin marketplace (recommended):

/plugin marketplace add rohitg00/awesome-claude-code-toolkit

Manual clone:

git clone https://github.com/rohitg00/awesome-claude-code-toolkit.git ~/.claude/plugins/claude-code-toolkit

One-liner:

curl -fsSL https://raw.githubusercontent.com/rohitg00/awesome-claude-code-toolkit/main/setup/install.sh | bash

Table of Contents


Plugins

Over 176 production-ready plugins that extend Claude Code with domain-specific capabilities.

Featured

PluginStarsDescription
pro-workflow1,800+Battle-tested Claude Code workflows from power users. Self-correcting memory, parallel worktrees, wrap-up rituals, 8 hook types, 5 agents, and the 80/20 AI coding ratio. Install: /plugin marketplace add rohitg00/pro-workflow
gstack68,200+Garry Tan's exact Claude Code setup: 6 opinionated tools that serve as CEO, Eng Manager, Release Manager, and QA Engineer.

All Plugins

PluginDescription
agento-patronumProtects sensitive files, credentials, and shell commands from unintended AI access via Claude Code hooks. Unlike settings.json deny rules, hooks are an enforcement layer you own and can verify. Ships with defaults for .env files, SSH keys, AWS credentials, and kubeconfig.
skills-janitorAudit, deduplicate, check, fix, and track usage of your Claude Code skills. 9 slash commands, zero dependencies
great_ctoFull SDLC pipeline plugin with 7 agents (tech-lead, senior-dev, qa-engineer, security-officer, devops, l3-support, project-auditor), 12-angle code review, 10 project archetypes, 13 compliance frameworks (SOC2/HIPAA/PCI-DSS/GDPR/ISO 27001), two-gate approval flow. Opus 4.7 advisor escalation, file-based, MIT
aws-cost-saverAWS cost optimization scanner with 173 automated checks, ML-powered rightsizing, and Zero Hallucination Pricing - Real result: 60% cost reduction
claude-agentic-coding-playbookEvidence-based practices for LLM-assisted development -- hooks, skills, scripts, and a best-practices guide with 58 citations. Includes 19+ guard/lifecycle hooks, investigation workflow, fleet indexing, and claude-loop for autonomous task queues.
claude-code-mcpRun Claude Code as a one-shot MCP server -- an agent in your agent. Permissions bypassed automatically. By Peter Steinberger. 1,100+ stars
claude-code-system-promptsExtracted system prompts from Claude Code -- 18 builtin tool descriptions, sub-agent prompts, utility prompts. Updated for each release. 5,900+ stars
claude-contextSemantic code search MCP server by Zilliz (Milvus creators). Hybrid BM25 + dense vector search. ~40% token reduction. 5,600+ stars
claude-cost-optimizerInstallable cost-mode skill (30-60% cost savings, up to 70% in strict mode) + 10 guides, 10 templates, budget hooks. Install: npx skills add Sagargupta16/claude-cost-optimizer
fractalRecursive project management for Claude Code. Decomposes goals into predicates, works the riskiest piece first, and re-evaluates as it learns
a11y-auditFull accessibility audit with WCAG compliance checking
accessibility-checkerScan for accessibility issues and fix ARIA attributes in web applications
adr-writerArchitecture Decision Records authoring and management
AgentLintLint your repo for AI agent compatibility. 33 evidence-backed checks across 5 dimensions. Claude Code plugin.
ai-prompt-labImprove and test AI prompts for better Claude Code interactions
analytics-reporterGenerate analytics reports and dashboard configurations from project data
android-developerAndroid and Kotlin development with Jetpack Compose
api-architectAPI design, documentation, and testing with OpenAPI spec generation
api-benchmarkerAPI endpoint benchmarking and performance reporting
api-referenceAPI reference documentation generation from source code
api-testerTest API endpoints and run load tests against services
aws-helperAWS service configuration and deployment automation
azure-helperAzure service configuration and deployment automation
backend-architectBackend service architecture design with endpoint scaffolding
bug-detectiveDebug issues systematically with root cause analysis and execution tracing
BouncerIndependent quality gate that uses Gemini to audit Claude Code's output. Includes Stop hook (automatic), quick audit skill, and deep audit with full tool access. One-liner install.
brooks-lintAI code reviews grounded in six classic engineering books (Brooks, Fowler, Martin, McConnell, Hunt & Thomas, Evans). Diagnoses code across 6 decay risk dimensions with structured findings (Symptom → Source → Consequence → Remedy). Supports PR review, architecture audit, tech debt assessment, and test quality review. v0.6 adds Mermaid dependency graphs.
ccmanagerCoding agent session manager supporting Claude Code, Gemini CLI, Codex, Cursor, Copilot, Cline, OpenCode, Kimi CLI. Smart auto-approval via Haiku, devcontainer support. 940+ stars
ccpmProject management using GitHub Issues + Git worktrees for parallel agent execution. Issue-analyze, epic-start, epic-merge commands. 7,600+ stars
ccusageCLI for analyzing Claude Code/Codex usage from local JSONL files. Daily, monthly, session, billing-window reports. Offline, zero API calls. 11,500+ stars
cc-costSingle-file Python CLI that parses Claude Code transcript JSONL and reports cost, prompt-cache hit rate, tool-call distribution, top expensive turns, and actionable optimization recommendations (--diagnose, --md, --top N). MIT, no third-party deps.
getburndLocal-first cost-control CLI for Claude Code. Reads ~/.claude/projects/*.jsonl, identifies 8 leak patterns (verbose context, tool loops, large file re-reads), prints savings estimates, generates a shareable report URL. MIT, zero telemetry.
building-multiagent-systemsArchitecture patterns for multi-agent systems: orchestrator-worker, pipeline, debate, and MapReduce topologies
bundle-analyzerFrontend bundle size analysis and tree-shaking optimization
chiefCLI that wraps Claude Code in a loop. Define a PRD, run chief, go do anything else. Commits after each task, picks up where it left off. Homebrew installable. 380+ stars
claudebaseBack up, restore, and sync your Claude Code config (settings, skills, agents, hooks, rules, memory, MCP) to a private GitHub repo. Named profiles, secret scanning, multi-machine conflict detection, automatic backups. 158 tests
changelog-genGenerate changelogs from git history with conventional commit parsing
changelog-writerDetailed changelog authoring from git history and PRs
ci-debuggerDebug CI/CD pipeline failures and fix configurations
claude-hooks-masteryComplete mastery guide for Claude Code hooks -- UV single-file Python scripts, sub-agents, meta-agent, team-based validation, AI-generated audio feedback. 3,300+ stars
claude-memAutomatically captures everything Claude does, compresses with AI, injects relevant context into future sessions. SQLite + full-text search. 35,900+ stars
claude-notifications-goCross-platform smart notifications -- 6 types, click-to-focus, context analysis, webhooks. Single Go binary, zero deps. 340+ stars
claude-opsBusiness operating system plugin for Claude Code. Morning briefings, unified inbox, autonomous PR merge, infrastructure monitoring, and YOLO autonomous mode.
claude-scaffoldnpx CLI that deploys CLAUDE.md, hooks, and 18 domain skills to any repository in one command. Skills auto-activate via hooks based on project context. Cross-repo sync via update --all. Install: npx claude-scaffold init
claude-recapPer-topic session memory using Shell hooks — archives each conversation topic as a separate Markdown summary. Two hooks, bash + Node.js, 100% local
clirank-mcp-server (npm)API discovery for agents -- scores 210+ APIs on CLI-friendliness across 11 signals. Find the right API for any task via MCP tools or REST (curl "https://clirank.dev/api/discover?q=send+emails"). No auth required
/chtChat persistence for Claude Code — 13 slash commands + hooks for saving conversations as local markdown files. Crash-proof auto-save via hooks, project-based organization, search, and management. npm: @kosoukhov/cht-cli
claude-rankSEO/GEO/AEO audit plugin — tells you why AI won't cite your site, then auto-fixes robots.txt, sitemap.xml, llms.txt, and JSON-LD. 170+ rules across 10 scanners, zero config
claude-soundsAudio feedback for Claude Code hooks — 10 events, 21 sounds, random rotation. macOS (afplay).
claude-code-hooks15 production-tested hooks from 160+ hours of autonomous operation. Destructive command blocker, branch guard, syntax check, context monitor, permission auto-approver. Bash, zero deps
claude-code-sessionsSession intelligence plugin. 11 skills for full-text search, token analytics, task management, session comparison, timeline views, and context recovery across all sessions. Includes a web dashboard. Zero runtime dependencies, read-only
cc-aws-keepaliveKeep Claude Code sessions alive through AWS credential expiry -- proactive expiration warnings, credential refresh bypass for Bedrock SSO/SAML, optional statusline countdown timer. 4 hook scripts, zero dependencies
cc-safe-setupOne command (npx cc-safe-setup) to install 6 essential safety hooks in 10 seconds. Zero dependencies
knowledge-graphBuilt on Anthropic internal engineering practices and Karpathy's AutoResearch methodology. A zero-dependency, git-native memory layer for Claude Code that persists learned context across sessions. Pure bash, ~3ms/event, privacy-first
claude-supermemoryPersistent memory across sessions and projects using Supermemory. User profile injection at session start, automatic conversation capture. 2,300+ stars
cortexPersistent memory for Claude Code — neuroscience-backed retrieval with thermodynamic decay, backed by 41 published papers. PostgreSQL + pgvector + sentence-transformers. 6 lifecycle hooks (SessionStart, UserPromptSubmit, PostToolUse, SessionEnd, Notification, SubagentStart), hierarchical recall, causal chains, knowledge graph navigation. Install and forget.
code-architectGenerate architecture diagrams and technical design documents
code-explainerExplain complex code and annotate files with inline documentation
code-guardianAutomated code review, security scanning, and quality enforcement
code-review-assistantAutomated code review with severity levels and actionable feedback
eliniscanAI full codebase scanner. Opens a separate Claude session for every file — reads every line, misses nothing. Finds bugs, security, performance issues and auto-fixes.
codebase-documenterAuto-document entire codebase with inline comments and API docs
codesightCLI token optimizer and AI context generator. Scans codebases to extract routes, schema, components, and dependencies for Claude Code, Cursor, Copilot, Codex, and Windsurf. 9x–13x token reduction. Zero runtime dependencies. npx codesight
color-contrastColor contrast checking and accessible color suggestions
commit-commandsAdvanced commit workflows with smart staging and push automation
complexity-reducerReduce cyclomatic complexity and simplify functions
compliance-checkerRegulatory compliance verification for GDPR, SOC2, and HIPAA
content-creatorTechnical content generation for blog posts and social media
context7-docsFetch up-to-date library documentation via Context7 for accurate coding
contract-testerAPI contract testing with Pact for microservice compatibility
cozempic✨ v1.2.x — Self-updating now, atomic writes, strict session guard, zero false positives on team detection. 13 pruning strategies, Agent Team protection, MCP server, JSONL doctor. Install: /plugin marketplace add Ruya-AI/cozempic
create-worktreesGit worktree management for parallel development workflows
cron-schedulerCron job configuration and schedule validation
css-cleanerFind unused CSS and consolidate stylesheets
cupClickUp CLI for AI agents with task management, sprints, and time tracking
data-privacyData privacy implementation with PII detection and anonymization
database-optimizerDatabase query optimization with index recommendations and EXPLAIN analysis
dead-code-finderFind and remove dead code across the codebase
debug-sessionInteractive debugging workflow with git bisect integration
dig2crawlUniversal web crawler with Claude-powered CSS selector discovery. 4-level AI extraction escalation (CSS, browser actions, Claude Vision, captcha). Rust.
dependency-managerAudit, update, and manage project dependencies with safety checks
deploy-pilotDeployment automation with Dockerfile generation, CI/CD pipelines, and infrastructure as code
desktop-appDesktop application scaffolding with Electron or Tauri
devops-automatorDevOps automation scripts for CI/CD, health checks, and deployments
discussDebate implementation approaches with structured pros and cons analysis
claw-army/claude-nodePython subprocess bridge for Claude Code CLI, giving Python code direct access to Claude Code native capabilities via stream-json
discoclawPersonal AI orchestrator that bridges Discord to Claude Code with durable memory, task tracking, and cron-based automation
jarvisTurns an idle Claude Max subscription into a 24/7 AI ops system — Discord bot, 76 scheduled tasks, 12 AI teams, local LanceDB RAG, 98% context compression via Nexus CIG, and 4-layer self-healing infrastructure. Uses claude -p headless mode at $0 extra cost.
jarvis-company-boardReal-time AI agent collaboration board built on Next.js 15 and SQLite WAL — 8 named AI board members debate decisions via SSE push, with a DEV task approval workflow and Railway deploy support.
dna-claude-analysisPersonal genome analysis toolkit that analyzes raw DNA data across 17 categories and generates a terminal-style HTML dashboard
codetapeThe flight recorder for AI coding — auto-records semantic traces and syncs README, CHANGELOG, CLAUDE.md. Zero deps. npx codetape init
doc-forgeDocumentation generation, API docs, and README maintenance
docker-helperBuild optimized Docker images and improve Dockerfile best practices
double-checkVerify code correctness with systematic second-pass analysis
e2e-runnerEnd-to-end test execution and recording for web applications
embedding-managerManage vector embeddings and similarity search
env-managerSet up and validate environment configurations across environments
env-syncEnvironment variable syncing and diff across environments
experiment-trackerML experiment tracking with metrics logging and run comparison
exploreSmart codebase exploration with dependency mapping and structure analysis
faf-skills31 Claude Code skills for persistent project context (.faf, application/vnd.faf+yaml). Scoring, sync, testing, publishing, MCP server creation, architecture docs. Anthropic MCP #2759.
feature-devFull feature development workflow from spec to completion
fractalRecursive project management plugin. Decomposes any goal into verifiable predicates, works on the riskiest unknown first. Features /fractal:run (idempotent state machine), /fractal:init, /fractal:patch, dry run mode, and incremental decomposition with re-evaluation.
finance-trackerDevelopment cost tracking with time estimates and budget reporting
fix-github-issueAuto-fix GitHub issues by analyzing issue details and implementing solutions
fix-prFix PR review comments automatically with context-aware patches
flutter-mobileFlutter app development with widget creation and platform channels
frontend-developerFrontend component development with accessibility and responsive design
gcp-helperGoogle Cloud Platform service configuration and deployment
gate4agentUniversal Rust transport for CLI AI agents (Claude Code, Codex, Gemini, OpenCode). Pipe/NDJSON, PTY, and ACP modes. Published on crates.io.
git-flowGit workflow management with feature branches, releases, and hotfix flows
github-issue-managerGitHub issue triage, creation, and management
harness-evolverLangSmith-native autonomous agent optimization. Multi-agent proposers evolve prompts, routing, tools, and architecture in isolated git worktrees. Install: npx harness-evolver@latest
helm-chartsHelm chart generation and upgrade management
idle-timingInjects hidden timing context (local time with UTC offset, idle seconds since last reply, previous-turn duration) into every user prompt so the model knows how long the conversation has been paused. Ships a statusline fragment for a live elapsed-time readout and a visible [after Xm Ys] note when you return from >10s idle. 57 tests, dual Unlicense/CC0.
immich-photo-managerTurn your self-hosted Immich photo library into a conversation — natural language search, geographic album curation, duplicate detection via perceptual hashing, library health audits, and interactive HTML galleries. 22 MCP tools, 11 skills, 5 slash commands
import-organizerOrganize, sort, and clean import statements
infrastructure-maintainerInfrastructure maintenance with security audits and update management
ios-developeriOS and Swift development with SwiftUI views and models
k8s-helperGenerate Kubernetes manifests and debug pod issues with kubectl
leapfrog-mcpMulti-session browser MCP server -- 15 parallel isolated Chromium sessions so multiple Claude Code terminals can browse simultaneously. 37 tools for navigation, extraction, interaction, network interception, and session profiles. 797 tests. Install: npx -y leapfrog-mcp
license-checkerLicense compliance checking and NOTICE file generation
lighthouse-runnerRun Lighthouse audits and fix performance issues
lightcmsAI-native CMS with 41 MCP tools for managing websites through natural language — pages, templates, assets, themes, collections, redirects, and more with full content versioning
linear-helperLinear issue tracking integration and workflow management
load-testerLoad and stress testing for APIs and web services
memory-profilerMemory leak detection and heap analysis
migrate-toolGenerate database migrations and code migration scripts for framework upgrades
migration-generatorDatabase migration generation and rollback management
model-context-protocolMCP server development helper with tool and resource scaffolding
model-evaluatorEvaluate and compare ML model performance metrics
monitoring-setupMonitoring and alerting configuration with dashboard generation
monorepo-managerManage monorepo packages with affected detection and version synchronization
mutation-testerMutation testing to measure test suite quality
myclaudeMulti-agent orchestration routing tasks to Claude Code, Codex, Gemini, and OpenCode based on complexity. OmO skill for intelligent routing. 2,400+ stars
nimbalystVisual workspace for building with Codex and Claude Code. Session and task manager. Visual editing
n8n-workflowGenerate n8n automation workflows from natural language descriptions
nexus-agentsIntelligent orchestration platform routing tasks to Claude, Gemini, Codex, and OpenCode via Budget→TOPSIS→LinUCB composite router. 30 MCP tools (orchestrate, consensus voting, research pipelines), 12 expert agents, 17 skills, plugin-native /agents + hooks. Install: /plugin marketplace add williamzujkowski/nexus-agents
onboarding-guideNew developer onboarding documentation generator
oh-my-claudecodeTeams-first multi-agent orchestration. 19 specialized agents, 28 skills. Full autonomous execution, Socratic questioning, N coordinated agents. 9,900+ stars
onWatchOpen-source Go CLI that tracks AI API quota usage across 7 providers (Synthetic, Z.ai, Anthropic, Codex, GitHub Copilot, MiniMax, Antigravity) with a background daemon (<50 MB RAM), zero telemetry, and a Material Design 3 web dashboard
obeyRule enforcement plugin. Save rules with natural language, enforce with 17 lifecycle hooks. Three scopes (global, stack-specific, project-local), active blocking via PreToolUse, completion checklists via Stop hook, audit trail, auto-detects rule-like language. Cross-platform.
opcodeTauri 2 desktop GUI and toolkit for Claude Code. Manage sessions, create custom agents with visual editor, usage analytics, MCP integration. 21,000+ stars
openapi-expertOpenAPI spec generation, validation, and client code scaffolding
optimizeCode optimization for performance and bundle size reduction
ORCHCLI runtime orchestrating Claude Code, Codex, and Cursor as typed agent teams with state machine (todo→review→done), auto-retry, inter-agent messaging, goals, and TUI dashboard
oss-autopilotOpen source contribution manager — tracks PRs across repos, discovers issues, diagnoses CI failures, drafts maintainer responses. 7 agents, interactive commands, MCP server. Install: /plugin marketplace add costajohnt/oss-autopilot
paco-framework1+
peon-pingWarcraft III Peon voice notifications (+ StarCraft, Portal, Zelda) for Claude Code and other agents. Desktop banners, auto-detects SSH/devcontainers. 3,900+ stars
perf-profilerPerformance analysis, profiling, and optimization recommendations
performance-monitorProfile API endpoints and run benchmarks to identify performance bottlenecks
planStructured planning with risk assessment and time estimation
preflight24-tool MCP server that catches vague prompts before they cost 2-3x in wrong→fix cycles. 12-category scorecards, correction pattern learning, cross-service contract awareness, session history search with LanceDB vectors, and cost estimation. npx preflight-dev
pr-reviewerReview pull requests with structured analysis and approve with confidence
product-shipperShip features end-to-end with launch checklists and rollout plans
production-grade14-agent autonomous pipeline — PM, Architect, Backend, Frontend, QA, Security, Code Review, DevOps, SRE, Data Scientist, Technical Writer, Skill Maker, Polymath co-pilot. Two-wave parallel execution, brownfield-safe.
product-org-os150+ skills and 12 role-based agents (CPO, VP Product, PM, PMM, BizOps, CI, and more) modeling a full product org. Two gateways: /product auto-routes to the right agent, /plt runs a multi-stakeholder leadership meeting. MIT. claude plugins install github:yohayetsion/product-org-os
project-scaffoldScaffold new projects and add features with best-practice templates
prompt-optimizerAnalyze and optimize AI prompts for better results
pulseLocal Channel plugin — push notifications into Claude Code sessions via HTTP POST. No Discord/Slack needed, just curl. Three levels (info/warn/error), source tracking, dedup.
PUIUX PilotAuto-configures Claude Code hooks, MCPs, and skills for any project. Scans 95+ project types, selects from 28+ hooks, scores quality (0-100), translates configs across AI tools. Safe: dry-run, atomic writes, backup + rollback.
python-expertPython-specific development with type hints and idiomatic refactoring
pulserDiagnostic CLI for Claude Code SKILL.md files — scans 8 rules, auto-classifies, prescribes fixes with templates, --fix with rollback
query-optimizerSQL query optimization and execution plan analysis
rag-builderBuild Retrieval-Augmented Generation pipelines
rapid-prototyperQuick prototype scaffolding with minimal viable structure
reporecallLocal codebase memory for Claude Code. Tree-sitter AST indexing (22 languages), hybrid keyword + vector search, call-graph traversal, hooks + MCP. Injects relevant context in ~5ms before Claude starts thinking. npm: @proofofwork-agency/reporecall
react-native-devReact Native mobile development with platform-specific optimizations
readme-generatorSmart README generation from project analysis
refactor-engineExtract functions, simplify complex code, and reduce cognitive complexity
regex-builderBuild, test, and debug regular expression patterns
release-managerSemantic versioning management and automated release workflows
responsive-designerResponsive design implementation and testing
review-squadMulti-perspective code review via dispatched subagent panels: experts, normie users, pedantic nitpickers, and real-user task runners
schema-designerDatabase schema design and ERD generation
screen-reader-testerScreen reader compatibility testing and ARIA fixes
security-guidanceSecurity best practices advisor with vulnerability detection and fixes
seed-generatorDatabase seeding script generation with realistic data
sitemdBuild websites from Markdown via MCP. 22 tools for creating pages, generating content, configuring settings, running SEO audits, and deploying static sites to Cloudflare Pages
simmerIterative artifact refinement using judge subagents that score against user-defined criteria across multiple rounds
slack-notifierSlack integration for deployment and build notifications
smart-commitIntelligent git commits with conventional format, semantic analysis, and changelog generation
sprint-prioritizerSprint planning with story prioritization and capacity estimation
technical-salesTechnical demo creation and POC proposal writing
the-pragmatic-pmPM leadership toolkit with 43 skills, 5 agents, 4 workflows. Covers PRD generation, OKR lifecycle, pricing, AI pricing, positioning, sales enablement, and quarterly planning.
terraform-helperTerraform module creation and infrastructure planning
test-data-generatorGenerate realistic test data and seed databases
test-kitchenParallel implementation exploration using competing subagents, with structured comparison and winner selection
test-results-analyzerAnalyze test failures, identify patterns, and suggest targeted fixes
test-writerGenerate comprehensive unit and integration tests with full coverage
tool-evaluatorEvaluate and compare developer tools with structured scoring criteria
type-migratorMigrate JavaScript files to TypeScript with proper types
ui-designerImplement UI designs from specs with pixel-perfect component generation
ultrathinkDeep analysis mode with extended reasoning for complex problems
unit-test-generatorGenerate comprehensive unit tests for any function or module
update-branchRebase and update feature branches with conflict resolution
vision-specialistImage and visual analysis with screenshot interpretation and text extraction
vibe-kanbanKanban-based orchestration for 10+ coding agents (Claude Code, Codex, Gemini CLI, Copilot, Amp). Isolated git worktrees per agent, inline diff review. 23,200+ stars
VibeGuardStop AI from hallucinating code. 88 rules + 13 hooks + 14 agents for real-time interception and static scanning across 5 languages
visual-regressionVisual regression testing with screenshot comparison
wshobson/agents112 specialized agents, 16 multi-agent workflow orchestrators, 146 skills, 79 tools in 72 focused plugins. 31,300+ stars
web-devFull-stack web development with app scaffolding and page generation
whatsapp-claude-pluginWhatsApp channel plugin for Claude Code -- connects as a linked device via Baileys v7 with bidirectional messaging, full media support, voice transcription, permission relay, and access control
workflow-optimizerDevelopment workflow analysis and optimization recommendations
background-timerBackground timer with task notifications -- set delayed checks without blocking conversation
claude-soundsAudio feedback for Claude Code hooks -- 10 events, 21 sounds, random rotation, customizable (macOS)

| notch-so-good | Pixel-art crab (Chawd) lives in your Mac's notch and watches Claude Code for you. Live session timers, color-coded notifications, 13 idle animations, mouse-reactive eyes, drowsiness system. Universal binary, one-line install: npx notch-so-good. MIT, 130+ users | | codebase-graph | Code intelligence MCP server — 42-language tree-sitter AST parsing, FalkorDB knowledge graphs, 0.944 MRR search quality. npm: @anthropic/codegraph | | ESP32-AI-Agent-Skill | Expert ESP32 embedded systems plugin — chip selection across 9 variants, GPIO validation with anti-bricking safety, Arduino/ESP-IDF code gen, LVGL v8–v9.5 refs, 60+ Waveshare board pinouts. Install: claude /install-plugin https://github.com/ezrover/ESP32-AI-Agent-Skill | | toprank | SEO + Google Ads plugin for Claude Code. Pulls real Search Console data and Google Ads API data, audits traffic and wasted ad spend, rewrites meta tags, generates JSON-LD schema, and ships the fixes. 9 skills across SEO, Ads, and cross-model review | | sniff-qa | AI-powered QA tool — 8 checks in one command. Source scanning (dead links, API endpoints, debug statements, broken imports), accessibility (axe-core), visual regression (pixelmatch), performance (Lighthouse), AI exploration, source/browser cross-referencing. MCP server included. 213 tests, Apache 2.0 | | humanizer-skill | Detects 37 AI writing patterns and rewrites text with human rhythm. 5 voice profiles (casual, professional, technical, warm, blunt). Based on burstiness/perplexity research. Zero dependencies | | ui-ux-suite | Design audit across 12 dimensions — color contrast, typography, layout, accessibility. Scans CSS, JSX, Tailwind configs. Quantified scores (1-10) with before/after fix code. WCAG 2.1, APCA, OKLCH. Zero deps | | claude-cybersecurity | AI-powered cybersecurity code review with 8 parallel agents. OWASP 2025, CWE Top 25, MITRE ATT&CK, 11 languages, 5 compliance frameworks, threat intelligence. Zero config. MIT | | Clarvia MCP | MCP quality scanner — scans any MCP server, returns AEO (Agent Engine Optimization) score. Indexes 27,843+ tools for instant lookup. 24 MCP tools (search, scan, compare, leaderboard, trending). npx -y clarvia-mcp-server | | OraClaw | Decision intelligence MCP server — 12 tools with 19 ML algorithms (multi-armed bandits, constraint solvers, forecasters, risk models, Q-learning, A*, simulated annealing). Sub-25ms responses, deterministic, 945 tests. npx @oraclaw/mcp-server | | US Business Data MCP | MCP server for US business data — search entities across 17 state Secretary of State databases, YellowPages leads, building permits from 47 cities, 20+ federal APIs (SEC, FDA, FEMA). Built in Go, on MCP Registry | | craft-statusline | Bash statusline plugin for Claude Code with state-aware git branch (ahead / behind / stashed / conflict / combined signals), context window with absolute-token traffic light (yellow at 400k tokens, red at 85%), 5h/7d rate limits, and optional cost. Bash 3.2 compatible, jq is the only dependency. Install: /plugin marketplace add derjochenmeyer/claude-code-craft-statusline | | mobile-spine | Scaffold for mobile teams whose Android, iOS, and Backend live in separate repos. Coordinates 4 specialized subagents (api / pm / android / ios) with hard repo boundaries via settings.json deny rules. /mobile-spine:init runs a 6-question interview and writes the full workspace; /feat drives a 4-question interview → 4-case classification (existing endpoint / new endpoint / new domain / backend not built). 4-class codebase inventory contract surfaced in every PR (Inventory: reuse X / extend Y / new Z / remove W). MIT. | | debian-packaging-agent-skill | Debian packaging skill covering debhelper, debian/rules, package metadata, lintian, and multi-binary packages for Ruby (gem2deb), Python (pybuild), Rust (debcargo), and Go (dh-golang). Loads language-specific reference docs on demand. Apache 2.0 | | unslop | Removes AI writing tells (tricolons, em-dash pileups, hedging stacks, sycophancy openers, stock vocabulary). Split lint/rewrite modes — run detection-only passes on your own text without rewriting. Five intensity levels. MIT licensed | | tailtest | Automatically generates and runs tests for every file Claude Code creates or modifies. PostToolUse hook detects changes, generates scenarios, runs them, and surfaces failures. 8 languages (Python, TypeScript, JavaScript, Go, Ruby, PHP, Java, Rust). Zero config, zero commands. | | dodo-agent-plugin | Official Dodo Payments plugin: 8 integration skills (checkout, subscriptions, webhooks, usage-based billing, credits, license keys, BillingSDK, best practices) and 2 MCP servers (live API via browser OAuth + docs search, no auth). Multi-agent: Claude Code, Codex, Cursor, OpenCode | | claude-time | Live local time + timezone injected into every prompt via UserPromptSubmit hook. Stops Claude from saying "tonight" at 9 AM. Also stamps every response with [HH:MM AM/PM TZ] so you can see when each message landed (useful when tasks stall). Zero config, zero deps beyond jq. MIT | | ejentum-mcp | Reasoning Harness for agentic AI: 4 MCP tools (reasoning, code, anti-deception, memory) over 679 engineered cognitive operations. Each call returns a structured scaffold the calling LLM ingests before its first token. Catches sycophancy, hallucination, and reasoning decay before they emerge. Companion skills/ directory ships SKILL.md files for autonomous routing in Claude Code. MIT, free tier 100 calls. | | claude-forge | "oh-my-zsh for Claude Code". Complete toolkit: 11 agents, 33 commands, 24 skills, 15 hooks (covering 21 lifecycle events) + 9 opt-in examples, 9 rules, 4 MCP servers (playwright, context7, jina-reader, chrome-devtools@0.23.0), statusLine. One install via curl ... install.sh or /plugin marketplace add sangrokjung/claude-forge. Includes TDD workflow, multi-reviewer pipeline (codex/gemini/security/architect), Chrome DevTools Lighthouse audits, 4-way independent skeptical review. Submitted to anthropics/claude-plugins-official. MIT. | | repo-visuals | Designs bespoke GitHub README hero visuals — animated GIF or static PNG — through a structured discovery dialog. Retina capture via Puppeteer + ffmpeg. Heroes merged into HTMLHint, Terminal.Gui, ast-graph. | | weft | Deterministic workflow tracking with event-sourced state — templates with skill chains, bounded loops, and per-step tool guards. Hooks block out-of-order tool calls; state survives compaction via an append-only event log. Stdlib-only Python core, 191 tests, MIT. Install: /plugin marketplace add dioptx/weft | | magic-cc-codex-worker | Turns OpenAI Codex into a pool of parallel agent workers for Claude Code. Each worker runs in its own git worktree to isolate concurrent edits. Resumable sessions, dual-model PR review (PR materialized in a detached worktree for the reviewer), role-based specialization (implementer/reviewer/planner), delegation-level knob (minimal/balance/max), bundled single-file MCP server. 9 slash commands, 3 subagents, 62 unit tests, CI on Node 20/22. Install: /plugin marketplace add wenqingyu/magic-cc-codex-worker then /plugin install magic-codex@magic-codex. License: PolyForm Noncommercial 1.0.0 (free for independent devs / research / nonprofits; commercial use requires separate license) | | notify | Cross-platform system notifications for Claude Code hooks — macOS (terminal-notifier) and Linux (notify-send). Duration filtering to suppress noisy short events, git context extraction (repo + branch), and contextual messages per hook type. MIT | | claude-snapshot | Portable Claude Code setup snapshots — export your settings, plugins, hooks, CLAUDE.md, and MCP configs as a .tar.gz, diff before applying, and restore on another machine in under 2 minutes. No network, no daemon, .bak safety on every apply. Node.js 18+, cross-platform (macOS + Linux). Install: /plugin marketplace add adhenawer/claude-snapshot | | ashlr-plugin | Open-source Claude Code plugin replacing the built-in Read/Grep/Edit/Bash tools with token-efficient versions backed by @ashlr/core-efficiency. Independently benchmarked at 57% token reduction on real codebases. 70+ tools across glob, grep, structural diff/edit, and an opt-in genome (LSP-style codebase index). Install: curl -fsSL plugin.ashlr.ai/install.sh \| bash | | temporal-core | Make Claude Code agents feel time pass — research-backed temporal awareness via 3 hooks (SessionStart + UserPromptSubmit + PreToolUse) that inject session elapsed and since last action signals into context. Bundled skill teaches pacing/deadline reasoning. Aher et al. 2026: explicit time surfacing → 6× deadline performance. Apache-2.0, zero runtime deps. | | nirecom/agents | Self-driving Claude Code + GitHub Copilot framework with hook-enforced workflow state machine (research → plan → tests → code → security-review → docs), private-info scanning (AWS/Anthropic keys, PEM certs, RFC 1918 IPs), three-stage planning with adversarial Codex review, OWASP-backed test categories, and cross-machine session sync. Windows-native (PowerShell-first) with Linux/macOS support. | | claude-channel-instagram | Instagram Graph API bridge for Claude Code -- comments, DMs, comment-to-DM bootstrap, audio transcription, pluggable extensions system. Official Meta API (no scraping). Apache-2.0, by RIA Systems (verified Meta Tech Provider). Landing: claude-plugins.riasistemas.com.br/instagram. Install: /plugin marketplace add riasistemas/claude-plugins then /plugin install instagram@riasistemas | | claude-channel-whatsapp | Official WhatsApp Business Cloud API bridge for Claude Code -- webhooks, OGG Opus audio, allowlist + permission relay scrubbing secrets. NOT Baileys/scraping -- uses Meta's official API with WABA tokens. Apache-2.0, by RIA Systems (verified Meta Tech Provider). Landing: claude-plugins.riasistemas.com.br/whatsapp. Install: /plugin marketplace add riasistemas/claude-plugins then /plugin install whatsapp@riasistemas | | axme-code | Persistent project memory across

More Harnesss

Harnesses

claude-simone

Structured project management harness for Claude Code — define milestones and sprints in markdown, then run execution loops that drive Claude through each task.

project-managementmilestonessprints+2
by Helmi
GitHub
Harnesses

Claude Squad

Multi-agent tmux orchestrator — spawn N isolated Claude Code sessions in parallel, each in its own git worktree, then merge the best results back to main.

multi-agentparalleltmux+3
by SMTG AI
GitHub
Harnesses

Claude Swarm

Distributed Claude agent swarms — agents communicate via MCP, share tool access, and collaborate on complex tasks with configurable topology and role specialization.

swarmdistributedmulti-agent+3
by parruda
GitHub

Command Palette

Search for a command to run...