A carefully crafted Claude Code statusline written in bash. Shows model, effort level, git branch (state-aware color palette), context window with absolute-token traffic light, rate limits, and optional cost.
★not rated 2 6mo agoA
tokens not measured
originalMIT
Deep Claude Code setup audit. Fetches latest docs, analyzes session history, usage patterns, and feature adoption. Runs 4 parallel agents — takes 2-20 minutes and uses significant token budget. For a fast local check, use /craft-project-audit.
Fast project health check. Structure completeness, namespace purity, file staleness, hook functionality, decisions format, memory adoption, dream history, setup quality — all from local files. Works with or without git. No agents, no external fetches, 15-30 seconds. For deep analysis with feature adoption and session…
Project maintenance through consolidation. Snapshots every change to .craft/dreams/ before applying. Forgets noise, strengthens patterns, resets capacity. Run after active sprints or when docs feel cluttered.
Set up a new project with complete Claude Code infrastructure, or enhance an existing project with missing pieces. Detects foreign structures and hook issues before touching anything.
Save a mid-session checkpoint. Writes .craft/PROJECTSTATE.md, .craft/BACKLOG.md, .craft/DECISIONS.md, optionally .craft/HANDOVER.md, then commits. Run manually via /craft-session-solidify or when the context monitor warns at 75%.
Check for updates to all installed craft skills and apply them. Also detects newly added skills not yet installed.
★not rated 2 6mo agoD25 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: