trace-claude-code
Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.
Find unused functions and dead code in the codebase
$ npx -y skills add parcadei/Continuous-Claude-v3 --skill dead-code --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/dead-codeContext preview
The summary Claude sees to decide when to auto-load this skill.
Find unused functions and dead code in the codebase
name: dead-code description: Find unused functions and dead code in the codebase allowed-tools: [Bash] keywords: [dead code, unused, cleanup, refactor, unreachable]
Find unused functions and dead code using TLDR static analysis.
# Scan entire project tldr dead . # Scan specific directory tldr dead src/ # Specify entry points (functions to exclude from analysis) tldr dead . --entry main cli test_ # Specify language tldr dead . --lang python tldr dead . --lang typescript
Dead code analysis: Total functions: 150 Dead functions: 12 Unused functions: - old_helper (src/utils.py:42) - deprecated_func (src/legacy.py:15) - _unused_method (src/api.py:230)
Works on Windows, Mac, and Linux (including WSL).
# Windows (PowerShell) tldr dead . # Mac/Linux tldr dead .
Functions matching entry patterns are excluded from dead code analysis:
# Custom entry points tldr dead src/ --entry main api_handler background_job
This skill replaces the session-start-dead-code hook with on-demand analysis.
| Approach | Pros | Cons | |----------|------|------| | Hook (removed) | Automatic | Slowed startup by 3s | | Skill (this) | On-demand, fast | Manual invocation |
# Impact analysis (who calls this?) tldr impact func_name . # Architecture layers tldr arch src/ # Full codebase structure tldr structure . --lang python
A persistent, learning, multi-agent development environment built on Claude Code Continuous Claude transforms Claude Code into a continuously learning system that maintains context across sessions, orchestrates specialized agents, and eliminates wasting
Repo: parcadei/Continuous-Claude-v3
Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.
Guide for integrating Agentica SDK with Claude Code CLI proxy
Reference guide for Agentica multi-agent infrastructure APIs