adopt
CommandUse when: user asks to put the claude-mem-lite steering block into the current project's CLAUDE.md (for example to share it with…
Use when: capturing a non-obvious lesson/gotcha/workaround after a tricky fix or surprising behavior. Writes a searchable observation (findable via mem_search + surfaced by recall hooks; still NOT memdir/L1 prompt). Skip for typos, renames, or user-preference rules.
> /plugin marketplace add sdsrss/claude-mem-lite> /plugin install claude-mem-lite@sdsrss
name: lesson description: "Use when: capturing a non-obvious lesson/gotcha/workaround after a tricky fix or surprising behavior. Writes a searchable observation (findable via mem_search + surfaced by recall hooks; still NOT memdir/L1 prompt). Skip for typos, renames, or user-preference rules."
Record a lesson / gotcha / workaround. Writes a searchable **observation** (`type=discovery` with the text as `lesson_learned`) so future sessions can find it via `mem_search` and the PreToolUse recall hooks surface it on the relevant files. Does NOT touch memdir — so lessons never end up in the auto-memory index Claude Code loads into every session, and do not conflict with Claude Code's auto-memory rules on what not to save there.
After you (or the user) solve a tricky bug or discover a non-obvious behavior:
Don't use for trivial fixes (typos, renames), for rules that belong in memdir (user preferences, project-wide conventions), or for general project notes (use `/claude-mem-lite:memory` or `mem_save` instead).
pre-tool-recall the next time the file is opened via Edit/Write.
want surfaced; `1` for minor gotchas.
Run via Bash — pass the full lesson text as the positional content, and a distilled version in `--lesson` so it lands in the high-weight `lesson_learned` field. `--lesson` is capped at 500 chars (longer values are rejected), so for a long lesson keep the full text in the positional content and trim `--lesson` to the core insight:
node "${CLAUDE_PLUGIN_ROOT}/cli.mjs" save "<full text>" \ --type discovery \ --title "<first 60 chars of text>" \ --lesson "<core insight, ≤500 chars>" \ [--files f1,f2,...] \ --importance <1|2|3>
Confirm to user with: `Lesson saved: #<id>`.
claude-mem-lite is a persistent memory (also called long-term memory or cross-session context) system for Claude Code — Anthropic's CLI coding agent.
Use when: user asks to put the claude-mem-lite steering block into the current project's CLAUDE.md (for example to share it with…
Use when: logging a known bug + repro steps you can't fix right now. Writes a searchable observation (findable via mem_search +…
Use when: querying past work, managing memories, or checking project history
Use when: user asks to remember something, after solving a non-obvious problem, or to capture key session findings
Use when: user wants to remove the claude-mem-lite steering block from the current project (or from every project Claude Code…
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.