Settings file Claude Code
Agent settings declaring 17 allowed tools.
Settings file Claude Code
Agent settings declaring 17 allowed tools.
Command
Run full review pipeline (CEO → design → engineering → DX) on a feature idea before coding. Inspired by gstack.
Command
Warn before destructive commands (rm -rf, DROP TABLE, git push --force, docker prune). Pairs with /freeze and /guard. Inspired by gstack.
Command
Summarize the current conversation into a short handoff doc for future sessions.
Command
Cross-model adversarial review — spawn kimi + opencode (or codex) for second opinions on a piece of code or decision.
Command
Structured extraction from a URL or local file into JSON/markdown. Inspired by google/langextract.
Command
Lock edits to a specific directory for the rest of the session. Inspired by gstack.
Command
Append an insight to the daily llm-wiki. Inspired by everything-claude-code + karpathy llm-wiki.
Command
Dispatch parallel Explore + Plan agents on a question. Inspired by obra/superpowers.
Command
Multi-source research on a topic (WebSearch + WebFetch + context7 + duckduckgo). Produces a cited brief.
Command
Weekly retrospective based on IMPROVEMENTSTATE.json across all projects. Inspired by gstack.
Command
Release the /freeze edit lock. Inspired by gstack.
Command
Search the persistent llm-wiki for existing notes on a topic.
Command
Download a video/podcast via yt-dlp, transcribe with whisper.cpp, save as markdown in llm-wiki.