By fatihkan
Orchestrates 30 AI agents with 84 commands and 62 skill categories for end-to-end development workflows — from project scaffolding, code review, and testing to deployment, SEO, marketing, and security auditing. Includes automated changelog and release management, Git history analysis, content production, accessibility and performance audits, OWASP vulnerability scanning, and incident post-mortems.
Quality audit command. Runs a systematic audit over code, structure, or process.
Project briefing command. Turns raw project ideas into structured, actionable briefs.
Daily statistics panel. Presents task, audit, event, and performance data as a unified table.
Technical debt mapping command. Systematically detects and prioritizes technical debt in the codebase.
Deep code review command. Comprehensive code analysis across security, performance, and architecture.
Paid advertising strategist - project-aware market research, campaign strategy, launch-readiness verdicts
API design expert - REST/GraphQL consistency, documentation, versioning strategy
Code history researcher - answers the 'why was it written this way?' question
Architecture design advisor - design patterns, system design, ADR creation
Quality assurance gate - verifies outputs, detects inconsistencies
Workflow automation skills using AI. Build chatbots, automate repetitive tasks, integrate LLMs into pipelines, design intent-based assistants. Triggers on: chatbot, automation, workflow, AI agent, RAG, LLM integration, intent recognition, conversation design.
Strategic consulting skills for organizations. Long-term planning, business strategy, change management, organizational design, competitive analysis, vision/mission frameworks. Triggers on: strategy, consulting, planning, organizational change, competitive analysis, business model, vision.
Content production and SEO writing skills. Blog posts, long-form content research, structured content frameworks, audience-targeted writing, content optimization. Triggers on: blog, content writing, article, copywriting, content strategy, content brief, SEO content, audience research.
Customer onboarding, retention, and success skills. Reduce churn through structured first-value moments, lifecycle messaging, NPS analysis, account health scoring. Triggers on: onboarding, customer success, retention, churn, NPS, customer health, lifecycle, expansion revenue.
Data analysis, visualization, machine learning, business intelligence, and data engineering skills. SQL, dashboards, statistical analysis, predictive models, data pipelines. Triggers on: data analysis, dashboard, BI, SQL, machine learning, statistics, data pipeline, ETL, predictive analytics.
Executes bash commands
Hook triggers when Bash tool is used
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.
Language / Dil: English · Turkce
Workflow management CLI for Anthropic Claude Code, Cursor, and Gemini CLI — built for Claude Opus 4.7 and Sonnet 4.6. Ships 30 AI subagents (incl. a virtual eng team, ads strategist, and market/SEO/data analysts), 84 slash commands (profile-based core/dev/content/pentest management since v1.26), 14 automation hooks, and 62 opt-in skill categories (25 general + 25 pentest-* advisory/defensive since v1.25 + 12 expo-* mobile dev lifecycle since v1.27) with prompt-aware auto-routing for both skills and commands (v1.20+ / v1.26+). OWASP Top 10 scans, code review, content production, mobile/web SEO, App Store market research with wishlist + gaps analysis. Cuts token consumption ~96% on repetitive workflows. v1.12+ adds multi-harness support — the same .claude/ tree compiles into Cursor and Gemini CLI assets. v1.16+ hardens CodeQL surface (TLS strict-first, DOM-based HTML parsing, URL hostname validation).
Render the demo:
brew install vhs && vhs assets/demo.tapeproducesassets/demo.gifdeterministically. The tape is text-checked into the repo so the GIF is reproducible.
| Channel | Command | Status |
|---|---|---|
| npm (primary) | npm i -g @fatihkan/badi | ✅ Live |
| Claude Code marketplace | /plugin install fatihkan/badi | ✅ Live (manifest in repo) |
| Homebrew (macOS / Linux) | planned — tap repo not yet published; use npm | ⏳ Planned |
| Scoop (Windows) | planned — bucket repo not yet published; use npm | ⏳ Planned |
Source of truth: npm. Other channels mirror the same @fatihkan/badi-<version>.tgz. Sha256/hashes are populated by the release workflow (.github/workflows/dist-publish.yml). Homebrew and Scoop channels are skeletoned in dist/ but the tap/bucket mirror repos (fatihkan/homebrew-badi, fatihkan/scoop-bucket) are not yet created — until then, use npm or the Claude Code marketplace.
As a Claude Code plugin (no Node.js required for install):
# Inside Claude Code
/plugin marketplace add fatihkan/badi
/plugin install badi@badi-marketplace
As an npm CLI (full feature set: 30 agents · 84 commands with profile management (v1.26+) · 14 hooks · 62 opt-in skill categories with auto-router):
npx @fatihkan/badi init # interactive harness picker
npx @fatihkan/badi init --harness cursor # non-interactive: Cursor only
npx @fatihkan/badi init --harness all # write files for every supported harness
The plugin path ships agents, slash commands, and skills via
/plugin install. The npm path adds hooks, the multi-harness compiler (Cursor / Gemini CLI), and the fullbadiCLI toolchain.
Badi runs on Windows out of the box: hooks are pure Node.js (no bash required), the scheduler uses Windows Task Scheduler, and badi doctor reports OS-aware status.
# PowerShell or cmd
npm install -g @fatihkan/badi
badi init --harness claude
badi doctor # OS / Bash / Sched / UTF-8 status
For Turkish/UTF-8 output in cmd, run chcp 65001 once or use Windows Terminal / PowerShell 7+. WSL users can install normally — Linux path is auto-detected.
| Harness | Rules | Commands | MCP | Subagents | Hooks | Skills |
|---|---|---|---|---|---|---|
| Claude Code | CLAUDE.md | 84 | .mcp.json | 30 | 14 | 62 |
| Cursor | .cursor/rules/badi-main.mdc | 84 | .cursor/mcp.json | — | — | — |
| Gemini CLI | GEMINI.md (merged) | inline | .gemini/settings.json | — | — | — |
| Windsurf (v1.30+) | .windsurfrules (merged) | inline | — | — | — | — |
| AGENTS.md (v1.30+) | AGENTS.md (merged) | inline | — | — | — | — |
npx claudepluginhub fatihkan/badi --plugin badiHarness-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
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development