shanraisshan

shanraisshan/agentic-engineering

Hook Claude Code

Runs when a git worktree is created, executing hooks.py via python3. From shanraisshan/agentic-engineering.

shanraisshan/agentic-engineering

Hook Claude Code

Runs when a git worktree is removed, executing hooks.py via python3. From shanraisshan/agentic-engineering.

shanraisshan/agentic-engineering

Hook Claude Code

Runs after instructions files are loaded, executing hooks.py via python3. From shanraisshan/agentic-engineering.

shanraisshan/agentic-engineering

Hook Claude Code

Runs when the agent asks you a question, executing hooks.py via python3. From shanraisshan/agentic-engineering.

shanraisshan/agentic-engineering

Hook Claude Code

Runs on the ElicitationResult event, executing hooks.py via python3. From shanraisshan/agentic-engineering.

shanraisshan/agentic-engineering

Hook Claude Code

Runs on the StopFailure event, executing hooks.py via python3. From shanraisshan/agentic-engineering.

shanraisshan/agentic-engineering

Hook Claude Code

Runs on the CwdChanged event, executing hooks.py via python3. From shanraisshan/agentic-engineering.

shanraisshan/agentic-engineering

Hook Claude Code

Runs on the FileChanged event for .envrc, .env and .env.local tool calls, executing hooks.py via python3. From shanraisshan/agentic-engineering.

shanraisshan/agentic-engineering

Hook Claude Code

Runs on the PermissionDenied event, executing hooks.py via python3. From shanraisshan/agentic-engineering.

shanraisshan/agentic-engineering

Settings file Claude Code

Agent settings declaring 27 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 6 allowed tools.

shanraisshan/agentic-engineering

Instructions file

Claude Code instructions for shanraisshan/agentic-engineering, covering claude.md, repository purpose, project structure, research workflow and workflow steps.

shanraisshan/draw-json-architecture-skill

Skill Claude CodeCodex

Draws an interactive HTML Architecture Viewer for any code flow the user names. Walks through seven research-driven steps (flow, name, repo research, lens colors, evidence flags, lens+mechanism per stop, build) and verifies links, claims, and generated artifacts before delivery.