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.
Plugin col from marketplace living-runtime in cihanatak/lr-memory. Commands read from the repo's manifest — 3 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
reportShows COL's record from its local logs - how many finished turns the claim check looked at, flagged and blocked, and whether the blocks turned out right; how the measurable predictions turned out (held, missed, which way the misses went, what still waits for a result); and what the key scan stopped
sh "${CLAUDE_PLUGIN_ROOT}/scripts/run.sh" hook
sh "${CLAUDE_PLUGIN_ROOT}/scripts/run.sh" hook
sh "${CLAUDE_PLUGIN_ROOT}/scripts/run.sh" hook
sh "${CLAUDE_PLUGIN_ROOT}/scripts/run.sh" hook
sh "${CLAUDE_PLUGIN_ROOT}/scripts/run.sh" hook
sh "${CLAUDE_PLUGIN_ROOT}/scripts/run.sh" hook
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
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
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.