ECC plugin
An engineering system for coding agents: 71 agents, 311 skills, hooks, memory, rules and the AgentShield security scanner
- 292,714 ★ on the repository
- Last commit
- MIT
Broad access
Why this level
- Installs hooks that run on agent events
- Modifies Claude Code and MCP configuration
- Runs an npm package with installer code
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/eccDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- Installs hooks that run on agent events
- Modifies Claude Code and MCP configuration
- Runs an npm package with installer code
This is third-party code. Review the repository files before installing.
What it does
ECC builds a plan, test, implement, review, verify, remember and improve loop into the agent. It ships specialized agents for planning, review, build repair, security and architecture, skills for TDD, research, docs, frontend and data, and hooks for enforcement and session summaries. AgentShield scans prompts, hooks, MCP config, permissions and secrets. It works best with Claude Code, has guided setup for Codex and Kimi Code, and capability-limited adapters for other harnesses.
Who it is for. Experienced Claude Code users ready to configure a complex system of hooks, rules and agents.
Good fit when
- You want mandatory tests and review built into the agent's workflow
- You need to scan agent config for secrets and risky permissions
- You work across Claude Code, Codex and Kimi Code
- You want memory and continuous learning across sessions
Not a fit when
- You want a light rule set without hooks and heavy context
- You are not ready to manage hook profiles and install scopes
Example request
Run a security review of changes on this branch and check MCP config with AgentShieldLimitations
Requires Node.js 18+, plus Git and Claude Code 2.1+ for the Claude plugin. Do not stack install methods in one harness, or skills and hooks get duplicated. ECC Pro for private repos is paid. The README warns to install only from official sources.
How to disable. Run npx ecc-universal@2.2.1 uninstall, optionally with --dry-run first. Individual hooks can be disabled with the ECC_DISABLED_HOOKS variable.
FAQ
Can I install ECC both as a plugin and manually?
No. Pick one method per harness, or skills, commands and hooks get duplicated. Installing into different harnesses is fine.
Where is it safe to install from?
Only the affaan-m/ECC repo, the ecc-universal and ecc-agentshield npm packages, the GitHub App, the ecc@ecc plugin slug and ecc.tools.
Discussion
No questions or reviews yet.
Related
PluginsAn operating layer for Claude Code and Codex: one /do entry point, project memory across sessions, safety hooks, cost telemetry and parallel agents
Knowledge-graph memory for agents: Claude Code and Codex plugins, an MCP server and a Python library
A memory and coordination layer for coding agents: specs and issues live in git while agents work in parallel
Multi-agent orchestration for Claude Code: teams, roles, autopilot and task routing across skills and subagents
A Rust app for macOS, Linux and Windows: skills, MCP servers, plugins, hooks and configs of 17 AI agents in one window, with a security audit
A skill plus hooks that keep a coding agent on task and cut speculative defenses, unread checksums and scope creep
README in short
ECC is described as an operating system for agent harnesses, open source under MIT. The README details the setup wizard, multi-harness install, one path per harness, reset and uninstall. A table lists agents, skills, commands, hooks, rules and AgentShield. There is a platform support matrix and a paid ECC Pro for private repos.
README badge
Original SKILL.md
--- name: accessibility description: Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support. standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android). metadata: origin: ECC --- # Accessibility (WCAG 2.2) This skill ensures that digital interfaces are Perceivable, Operable, Understandable, and Robust (POUR) for all users, including those using screen readers, switch controls, or keyboard navigation. It focuses on the technical implementation of WCAG 2.2 success criteria. ## When to Use - Defining UI component specifications for Web, iOS, or Android. - Auditing existing code for accessibility barriers or compliance gaps. - Implementing new WCAG 2.2 standards like Target Size (Minimum) and Focus Appearance. - Mapping high-level design requirements to technical attributes (ARIA roles, traits, hints). ## Core Concepts - **POUR Principles**: The foundation of WCAG (Perceivable, Operable, Understandable, Robust). - **Semantic Mapping**: Using native elements over generic containers to provide built-in accessibility. - **Accessibility Tree**: The representation of the UI that assistive technologies actually "read." - **Focus Management**: Controlling the order and visibility of the keyboard/screen reader cursor. - **Labeling & Hints**: Providing context through `aria-label`, `accessibilityLabel`, and `contentDescription`. ## How It Works ### Step 1: Identify the Component Role Determine the functional purpose (e.g., Is this a button, a link, or a tab?). Use the most semantic native element available before resorting to custom roles. ### Step 2: Define Perceivable Attributes - Ensure text contrast meets **4.5:1** (normal) or **3:1** (large/UI). - Add text alternatives for non-text content (images, icons). - Implement responsive reflow (up to 400% zoom without loss of function). ### Step 3: Implement Operable Controls - Ensure a minimum **24x24 CSS pixel** target size (WCAG 2.2 SC 2.5.8). - Verify all interactive elements are reachable via keyboard and have a visible focus indicator (SC 2.4.11). - Provide single-pointer alternatives for dragging movements. ### Step 4: Ensure Understandable Logic - Use consistent navigation patterns. - Provide descriptive error messages and suggestions for correction (SC 3.3.3). - Implement "Redundant Entry" (SC 3.3.7) to prevent asking for the same data twice. ### Step 5: Verify Robust Compatibility - Use correct `Name, Role, Value` patterns. - Implement `aria-live` or live regions for dynamic status updates. ## Accessibility Architecture Diagram ```mermaid flowchart TD