{
  "id": "page:library-everything-claude-code",
  "_kind": "Page",
  "_file": "wiki/library/everything-claude-code.md",
  "_cluster": "wiki",
  "attributes": {
    "nodeKind": "Page",
    "title": "Everything Claude Code Methodology (Library)",
    "displayName": "Everything Claude Code Methodology (Library)",
    "slug": "library/everything-claude-code",
    "articlePath": "wiki/library/everything-claude-code.md",
    "article": "\n# Everything Claude Code Methodology\n\nPerformance optimization system for AI agent harnesses, adapted from the [Everything Claude Code](https://github.com/affaan-m/everything-claude-code) project. Integrates specialized subagents, skills, continuous learning, security scanning, and research-first development workflows into babysitter process definitions.\n\n## Core Principles\n\n1. **Research-First Development**: Always investigate existing solutions before writing code\n2. **TDD Enforcement**: Red-Green-Refactor is mandatory; 80% coverage threshold\n3. **Multi-Dimensional Review**: 4-axis code review with confidence-gated reporting (>= 80%)\n4. **AgentShield Security**: 5-category security scanning with 102 static analysis rules\n5. **Continuous Learning**: Auto-extract patterns from sessions and convert to reusable skills\n6. **Context Engineering**: Dynamic context injection, mode switching, strategic compaction\n7. **Evidence-Based Verification**: All claims backed by exit codes, coverage numbers, or test results\n\n## Process Files (5)\n\n| File | Process ID | Description |\n|------|-----------|-------------|\n| `ecc-orchestrator.js` | `methodologies/everything-claude-code/ecc-orchestrator` | Full lifecycle: planning -> TDD -> implementation -> review -> security -> deploy -> learning |\n| `ecc-tdd-workflow.js` | `methodologies/everything-claude-code/ecc-tdd-workflow` | TDD cycle: strategy -> RED -> GREEN -> REFACTOR -> coverage convergence |\n| `ecc-security-pipeline.js` | `methodologies/everything-claude-code/ecc-security-pipeline` | AgentShield: 5-category parallel scan -> red team -> report synthesis |\n| `ecc-continuous-learning.js` | `methodologies/everything-claude-code/ecc-continuous-learning` | Learning: extract -> evaluate -> create skills -> organize -> export |\n| `ecc-multi-service.js` | `methodologies/everything-claude-code/ecc-multi-service` | Multi-service: discover -> cascade/parallel build -> PM2 -> integration test |\n\n## Agents (8)\n\n| Agent | Role | Used In |\n|-------|------|---------|\n| `planner` | Research-first implementation planning | Orchestrator |\n| `architect` | System design with testability focus | Orchestrator, Multi-Service |\n| `tdd-guide` | Red-Green-Refactor enforcement | Orchestrator, TDD Workflow |\n| `code-reviewer` | Multi-dimensional quality review | Orchestrator |\n| `security-reviewer` | AgentShield 5-category scanning | Orchestrator, Security Pipeline |\n| `build-resolver` | Build error resolution | Orchestrator, Multi-Service |\n| `e2e-runner` | Playwright POM end-to-end testing | Orchestrator, Multi-Service |\n| `refactor-cleaner` | Review-guided code cleanup | Orchestrator |\n\n## Skills (8)\n\n| Skill | Purpose |\n|-------|---------|\n| `tdd-enforcement` | Red-Green-Refactor with 80% coverage gating |\n| `security-scanning` | AgentShield 5-category audit with 102 rules |\n| `continuous-learning` | Pattern extraction and skill creation pipeline |\n| `context-engineering` | Dynamic context injection and strategic compaction |\n| `multi-service-orchestration` | PM2, cascade/parallel execution, cross-service testing |\n| `code-review-pipeline` | 4-dimension review with confidence gating |\n| `research-first-dev` | Investigate before implementing |\n| `eval-harness` | Agent and skill quality benchmarking |\n\n## Key Patterns\n\n- **Remediation Loop**: Review findings trigger refactor-cleaner, re-review, max 2 cycles\n- **Coverage Convergence**: Iterative test addition until 80% threshold met (max 3 iterations)\n- **Parallel Execution**: Code review and security scan run concurrently\n- **Breakpoints**: Plan review, coverage threshold, critical findings, deployment approval\n- **Cascade Execution**: Topological build order for dependent services\n- **Worktree Parallelism**: Git worktree isolation for independent service builds\n\n## Attribution\n\nAdapted from [Everything Claude Code](https://github.com/affaan-m/everything-claude-code) by Affaan M.\n",
    "documents": [
      "specialization:everything-claude-code"
    ]
  },
  "outgoingEdges": [
    {
      "from": "page:library-everything-claude-code",
      "to": "specialization:everything-claude-code",
      "kind": "documents"
    }
  ],
  "incomingEdges": [
    {
      "from": "page:index",
      "to": "page:library-everything-claude-code",
      "kind": "contains_page"
    }
  ]
}