Everything Claude Code Harness
Install and tune a full Claude Code (and cross-editor) harness with skills, hooks, memory, slash commands, subagents, and security scanning in one pass.
Overview
Everything Claude Code harness is an agent skill most often used in Build (also Operate, Ship) that installs and optimizes a full AI coding harness—skills, hooks, memory, commands, subagents, and security scanning—for Cl
Install
npx skills add https://github.com/aradotso/trending-skills --skill everything-claude-code-harnessWhat is this skill?
- Plugin marketplace flow: `/plugin marketplace add` and `/plugin install everything-claude-code@everything-claude-code`
- Manual clone path with `./install.sh` for language-specific rule packs
- Bundles skills, instincts, memory hooks, slash commands, and security scanning in one harness
- Documented for Claude Code, Cursor, Codex, OpenCode, and Antigravity
- Positioned as a production harness evolved from 10+ months of daily use
- Evolved from 10+ months of daily real-world use
- Supports Claude Code, Cursor, Codex, OpenCode, and Antigravity
Adoption & trust: 1.7k installs on skills.sh; 31 GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are using Claude Code or a similar agent daily but lack a cohesive setup of skills, hooks, memory, commands, and security checks, so every session starts from scratch.
Who is it for?
Solo builders standardizing Claude Code (or Cursor/Codex) on a new repo or after outgrowing a minimal plugin list.
Skip if: Builders who only need a single narrow integration skill with no harness, hooks, or cross-session memory—install a task skill instead.
When should I use this skill?
Triggers include “set up everything claude code”, “optimize my claude code setup”, “install ecc plugin”, “configure ai agent harness performance”, and “set up hooks and memory for claude code”.
What do I get? / Deliverables
After setup, your editor runs with ECC’s plugin or cloned bundle—rules, skills, hooks, and scanners aligned—so agents follow consistent workflows instead of ad-hoc prompts.
- Installed ECC plugin or cloned harness with language rules
- Configured skills, hooks, commands, and security scanning workflow
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Build because the skill’s triggers center on installing plugins, rules, and agent performance tooling—not on shipping or growth work. Agent-tooling is the right subphase: it packages subagents, reusable skills, custom commands, hooks, and scanner setup for daily coding agents.
Where it fits
Run marketplace install on day one so subagents, skills, and hooks load before the first feature branch.
Clone manually and run `./install.sh typescript` to align language rules with your stack.
Enable the bundled security scanning habits before merging agent-generated changes.
Tune memory hooks and custom commands when session quality drifts after months of shipping.
How it compares
Use for a full agent harness and performance kit, not a lone MCP server or one-off codegen snippet.
Common Questions / FAQ
Who is everything-claude-code-harness for?
Indie and solo developers who ship with Claude Code, Cursor, Codex, or similar agents and want marketplace or script-based installation of skills, hooks, commands, and security tooling in one system.
When should I use everything-claude-code-harness?
Use it during Build when you set up or optimize your agent editor; again in Ship when you add security scanning habits; and in Operate when you refine hooks and memory as the repo grows.
Is everything-claude-code-harness safe to install?
It advertises security scanning as part of the harness; review the Security Audits panel on this Prism page and inspect hook/command permissions in the repo before enabling on sensitive codebases.
SKILL.md
READMESKILL.md - Everything Claude Code Harness
# Everything Claude Code (ECC) — Agent Harness Performance System > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. Everything Claude Code (ECC) is a production-ready performance optimization system for AI agent harnesses. It provides specialized subagents, reusable skills, custom slash commands, memory-persisting hooks, security scanning, and language-specific rules — all evolved from 10+ months of daily real-world use. Works across Claude Code, Cursor, Codex, OpenCode, and Antigravity. --- ## Installation ### Option 1: Plugin Marketplace (Recommended) ```bash # Inside Claude Code, run: /plugin marketplace add affaan-m/everything-claude-code /plugin install everything-claude-code@everything-claude-code ``` ### Option 2: Manual Clone ```bash git clone https://github.com/affaan-m/everything-claude-code.git cd everything-claude-code # Install rules for your language stack ./install.sh typescript # Multiple languages: ./install.sh typescript python golang swift # Target a specific IDE: ./install.sh --target cursor typescript ``` ### Install Rules (Always Required) Claude Code plugins cannot auto-distribute rules — install them manually via `./install.sh` or copy from `rules/` into your project's `.claude/rules/` directory. --- ## Directory Structure ``` everything-claude-code/ ├── .claude-plugin/ # Plugin and marketplace manifests │ ├── plugin.json │ └── marketplace.json ├── agents/ # Specialized subagents (planner, architect, etc.) ├── commands/ # Slash commands (/plan, /security-scan, etc.) ├── skills/ # Reusable skill modules ├── hooks/ # Lifecycle hooks (SessionStart, Stop, PostEdit, etc.) ├── rules/ │ ├── common/ # Language-agnostic rules │ ├── typescript/ │ ├── python/ │ ├── golang/ │ └── swift/ ├── scripts/ # Setup and utility scripts └── install.sh # Interactive installer ``` --- ## Key Commands After installation, use the namespaced form (plugin install) or short form (manual install): ```bash # Planning & architecture /everything-claude-code:plan "Add OAuth2 login flow" /everything-claude-code:architect "Design a multi-tenant SaaS system" # Research-first development /everything-claude-code:research "Best approach for rate limiting in Node.js" # Security /everything-claude-code:security-scan /everything-claude-code:harness-audit # Agent loops and orchestration /everything-claude-code:loop-start /everything-claude-code:loop-status /everything-claude-code:quality-gate /everything-claude-code:model-route # Multi-agent workflows /everything-claude-code:multi-plan /everything-claude-code:multi-execute /everything-claude-code:multi-backend /everything-claude-code:multi-frontend # Session and memory /everything-claude-code:sessions /everything-claude-code:instinct-import # PM2 orchestration /everything-claude-code:pm2 # Package manager setup /everything-claude-code:setup-pm ``` > With manual install, drop the `everything-claude-code:` prefix: `/plan`, `/sessions`, etc. --- ## Hook Runtime Controls ECC hooks fire at agent lifecycle events. Control strictness at runtime without editing files: ```bash # Set hook strictness profile export ECC_HOOK_PROFILE=minimal # Least intrusive export ECC_HOOK_PROFILE=standard # Default export ECC_HOOK_PROFILE=strict # Maximum enforcement # Disable specific hooks