my-claude-code-mods

Execution profiler for Claude Code: model wait vs tools vs subagents, live, with OTLP export

Assumption Tracker

Blast Radius

Command Shelf

Context waste analyzer: what fills the window, re-reads, near-duplicate outputs, what compaction kept, advice

Decision Ledger

Dependency Lens

Env Doctor

Handoff Pack

Repeated-failure detective: evidence-backed Bash retry and edit/retry cases, live pane and investigation prompts

Shows the selected model and observed main-thread effort in a colored band above the prompt

Persistent pinned memos and clickable todos above the prompt, isolated by folder and session

Review Queue

Scope Guard

Agent Time Machine: a branching timeline of tool calls with shadow-git snapshots — inspect, diff, explain test failures, restore, branch, compare, re-run

Fully local ASCII runner for request failures and short breaks, with jump controls and a saved best score

Verify Board