rem-reflect

1# Self Learning
2 
3> **Before you use it.** Sno Station sets the sharing level when it installs, by mode: `full` for `agent-native` and
4> `rem-enhanced`, `metadata-only` for `local-first`; it never overwrites a choice you already made. At `full`, this tool sends
5> the text of your Claude Code, Codex, Hermes, OpenClaw and Cursor sessions and every installed skill to Sno's cloud. It uses your
6> Claude and Codex login in place and copies only Cursor's login into its isolated home to label sessions. In `local-first` nothing is sent to Sno, but the
7> text of a few sessions a night still goes to each session's own agent account when this tool asks it for lessons; Hermes and OpenClaw use their own login without a credential copy.
8> "What a run reads, copies and uploads" below lists everything.
9> Turn uploading off at any time with `sno station consent off`.
10 
11Self Learning (`rem-reflect`) reads this machine's Claude Code, Codex, Hermes, OpenClaw and Cursor sessions once a day. When the Sno Station
12settings select `agent-native` or `rem-enhanced`, each session's own CLI (on the
13host's default model) conservatively decides keep/drop and labels its outcome. Each completed run
14is sent through `sno rem judge`; that command permits session and skill uploads only at full consent.
15Only `rem-enhanced` uses the returned judgments, experience pages, skill proposals and lessons
16in its report and local store. `agent-native` keeps its local report and saves returned links
17…