By linder3hs
Reusable AI coding harness: planner, code-reviewer, security-reviewer, test-engineer and scaffolder agents, with matching skills and slash commands.
Plan a feature before coding — design, files to change, verification.
Review the current diff for bugs, simplification, and security.
Scaffold a new component, route, module, or project skeleton.
Write and run tests for the given code (or recent changes).
Reviews diffs and PRs for correctness bugs, simplification, reuse, and efficiency. Use proactively right before merging, after finishing a change, or when the user asks to "review", "check my code", or "look at this diff".
Designs features and architecture before any code is written. Use when starting a non-trivial feature, weighing approaches, or when the user asks to "plan", "design", or "think through" something. Returns a step-by-step implementation plan, not code.
Bootstraps new projects, modules, components, or routes following the project's existing conventions. Use when the user asks to "scaffold", "set up", "create a new component/route/module", or "bootstrap" something.
Audits code for security vulnerabilities — injection, auth/authorization flaws, secrets, trust-boundary violations, OWASP Top 10. Use when reviewing auth/payment/input-handling code, before shipping security-sensitive changes, or when the user asks for a "security review" or "audit".
Writes and runs tests, fills coverage gaps, and diagnoses failing tests. Use when the user asks to "add tests", "write tests", "improve coverage", or after implementing a feature that needs test coverage.
Plan a feature end-to-end before coding — clarify intent, explore existing code for reuse, design the approach, list files to change, and define how to verify. Use before implementing any non-trivial feature or when asked to plan or design work.
QA a web app/UI in a real browser — navigate flows, verify state, catch console/network errors, take screenshots as evidence. Use when asked to QA, test the site, verify a deployment, or confirm a UI feature works end-to-end.
Review the current diff/PR for correctness bugs, reuse, simplification, and efficiency. Use before merging, after finishing a change, or when asked to review code.
Bootstrap a new project, module, component, or route following existing conventions (or sensible Next.js/React/TS defaults for a fresh repo). Use when asked to scaffold, set up, or create a new component/route/module/project.
Audit code for exploitable security vulnerabilities — injection, auth/authorization flaws, secrets, trust-boundary violations, OWASP Top 10. Use when reviewing security-sensitive code (auth, payments, input handling) or when asked for a security audit. Defensive use only.
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.
A reusable AI coding harness for Claude Code. One source of truth for
your agents, skills, slash commands, hooks and CLAUDE.md templates — installed into any project
with one command, updated everywhere with a single git pull.
Built for a Next.js 16 / React 19 / TypeScript + Node/Fastify workflow, but works in any repo.
| Type | Items |
|---|---|
| Slash commands | /plan · /review · /test · /scaffold |
| Subagents | planner · code-reviewer · security-reviewer · test-engineer · scaffolder |
| Skills | plan-feature · review-diff · security-audit · write-tests · qa-browser · scaffold-project |
| Hooks (opt-in) | auto-format on save (prettier) · guard against rm -rf / force-push / DROP TABLE |
| Templates | stack-aware CLAUDE.md (Next.js / Node / generic) |
| Stack refs | stacks/nextjs-react.md, stacks/node-fastify.md (loaded on demand) |
bash install.sh # links bin/setup-ai → ~/.local/bin/setup-ai
# ensure ~/.local/bin is on PATH
cd ~/dev/my-app
setup-ai install # symlinks the harness into ./.claude/ + drops a CLAUDE.md
setup-ai install --with-hooks # also enable format + guard hooks
Then open Claude Code in that project — /help lists the commands, /agents lists the subagents.
setup-ai install symlinks each file from core/{agents,skills,commands} into the project's
.claude/. Because they're symlinks, editing a skill here updates every project instantly — no
reinstall. A .claude/.setup-ai-manifest.json records exactly what was installed for clean updates
and removal. Your project's own .claude/ files are never overwritten.
setup-ai install [path] [--with-hooks] [--force] install into a project (default: cwd)
setup-ai update [path] sync new files, prune dead links
setup-ai list [path] show what's installed
setup-ai uninstall [path] remove only setup-ai's files
setup-ai doctor [path] check for broken links / version drift
setup-ai version
cd ~/dev/setup-ai && git pull # symlinked projects pick up changes immediately
setup-ai update # in a project, only if files were added/removed
core/agents/ core/skills/<name>/SKILL.md core/commands/ ← the harness (symlinked in)
hooks/hooks.json templates/CLAUDE.*.md stacks/*.md
bin/setup-ai install.sh
.claude-plugin/marketplace.json + core/.claude-plugin/plugin.json ← optional: install as a plugin
The repo is also a published Claude Code plugin marketplace. From any project, in Claude Code:
/plugin marketplace add linder3hs/setup-ai
/plugin install setup-ai@setup-ai
(Or point at a local checkout instead of GitHub: /plugin marketplace add ~/dev/setup-ai.)
This namespaces the commands (/setup-ai:plan) and skips the symlink installer — useful for
sharing with a team. The setup-ai CLI remains the simpler path for solo, always-latest use.
Add a new skill: create core/skills/<name>/SKILL.md with a description frontmatter. Add an
agent: drop core/agents/<name>.md. Add a command: core/commands/<name>.md. Run
setup-ai update in your projects (or just git pull — symlinks already point at the new files
once you re-run install/update to link the new paths).
npx claudepluginhub linder3hs/setup-ai --plugin setup-aiComprehensive 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.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
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.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.