Wiring

Catches the gap between building infrastructure and actually wiring it into your execution path. If you've ever written 500 lines of orchestration logic only to realize nothing imports it, or created a hook that's not registered in settings.json, this is your checklist. It walks through the four step verification: entry point exists, call graph traced, integration tested, no dead code. The examples hit close to home, like building an entire DAG orchestration system with 18 agent types where the router just returns a hardcoded string. The detection scripts are immediately useful for grepping orphaned modules and unregistered hooks before you mark something done.

skills.sh installs: 486
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill wiring --agent claude-code

Installs into .claude/skills of the current project.

Files

Wiring Verification

When building infrastructure components, ensure they're actually invoked in the execution path.

Pattern

Every module needs a clear entry point. Dead code is worse than no code - it creates maintenance burden and false confidence.

The Four-Step Wiring Check

Before marking infrastructure "done", verify:

Entry Point Exists: How does user action trigger this code?
Call Graph Traced: Can you follow the path from entry to execution?
Integration Tested: Does an end-to-end test exercise this path?
No Dead Code: Is every built component actually reachable?

DO

Verify Entry Points

# Hook registered?
grep -r "orchestration" .claude/settings.json

# Skill activated?
grep -r "skill-name" .claude/skill-rules.json

# Script executable?
ls -la scripts/orchestrate.py

# Module imported?
grep -r "from orchestration_layer import" .