Plugin marketplace
Claude Code plugins from LR (Living Runtime), built for better use of the intelligence that is already there: memory that survives compaction and spans every session, COL (Cognitive Operating Loop), which checks claims against what actually ran, and the mind panel, one local page that shows where each of the layer's 13 aims stands, from your own files.
Add this marketplace
Then install any plugin below by name — each page has its exact command.
A verbatim working note across compaction, the turns of earlier sessions that each prompt brings back (the cue), a search over every past session (the recall skill), and a daily sleep pass that turns your own words into memory rules (the sleep skill). The note, the cue and the search are local and spend no model tokens.
2 skills · hooks
Cognitive Operating Loop: predict, act, check. Checks Claude's last message against what ran (commits it names, files it cites, test counts it gives), keeps a ledger of measurable predictions before long jobs and irreversible steps and compares them with the results, stops a commit or push that would carry a key, and asks for rival explanations when a fix does not hold. Local; no model calls.
1 skill · hooks
The mind panel: one local page for LR Memory, COL and scnc. For each of 13 aims it shows what the aim is, how it is measured, what the last measurement says, and live numbers read from your own logs, transcripts and memory files when the page is made. Every number names its source; nothing is sample data. Standard library only; no network, no model calls.
1 skill
Shows how many plugins this repo ships, and links here.