Create project.md (PRD), brand.md (brand guidelines), and CLAUDE.md (technical config) for any project. Interactive workflow with audit, archetype-based branding, and stack-specific optimization. Supports Laravel, Flutter, Vue2/3, Nuxt2/3, TailwindCSS, Alpine.js, and more.
Cross-project, verification-first memory for Claude Code — the layer beyond the built-in Auto Dream. Shares memory across your whole fleet (a governed global store, replicated into every project) and verifies facts against the live code (grep/file/git), dropping what it can't confirm — fact-checked, fleet-wide memory.
Beta-tests the consolidate-memory "dream" skill ITSELF — the QA companion to it. A deterministic invariant oracle plus a judgment-lens skill (/dream-beta-test) that finds defects, regressions, and dishonest reports in the dream/consolidation skill, honest by construction (confirmed defects are kept separate from…
Human-in-the-loop context compaction for Claude Code. You choose which turns survive; a SessionStart hook re-injects them deterministically after every compact and resume.
Furl context compression for Claude Code: bundles the Furl MCP server (furlcompress / furlretrieve / furlstats / furlpurge / furlsearch / furllist) and a fail-open PostToolUse hook that shrinks large tool outputs before they land in context. Originals stay byte-exactly retrievable via > markers.
Cross-tool context bridge between Claude Code and Codex. Logs your conversation and exposes it to the other tool so you can hand off plans, share context, and pick up where the other tool left off.
Keeps a project's architectural documentation in sync with its code by having Claude maintain modular docs as it works, instead of relying on a single static file or a human-run doc pass.
Plan-driven, short-session workflow for Claude Code. Externalize state to PLAN.md / HANDOFF.md and do one task per fresh session to beat context rot. Skills: using-planflow, plan, next, handover.
Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.
Persistent, cross-agent session handoff. Captures what you do in each project and keeps a lossless, human-readable handoff doc so the next session — in Claude Code or Cursor — resumes exactly where you left off.
Verbatim recall across Claude Code sessions, plus a gate that stops oversized skills from flooding the prompt. Pure Node, no dependencies, no API calls.