workinglisted
Install: claude install-skill backchainai/backchain-plugins
# Working Memory
Manage ephemeral `.memory/` directories for persisting structured conversation state across multi-day Claude Code sessions. Three commands cover the full lifecycle:
| Command | Purpose |
|---------|---------|
| `/engram:working checkpoint` | Create or update `.memory/` with current conversation state |
| `/engram:working promote` | Move `.memory/` artifacts to permanent knowledge locations |
| `/engram:working cleanup` | Delete promoted content, preserve the directory |
The skill is invoked as `/engram:working` (the plugin-qualified skill name) followed by the subcommand. Natural-language phrasings like "checkpoint working memory" trigger the same dispatch.
## Working memory vs auto memory
This skill complements [Claude Code's native auto memory](https://code.claude.com/docs/en/memory). They serve different purposes:
| | Working memory (this skill) | Auto memory (native) |
|---|---|---|
| **Trigger** | User-initiated (`/engram:working checkpoint`) | Automatic (Claude decides what's worth remembering) |
| **Content** | Structured work state — todos, decisions, questions | Implicit learnings — corrections, preferences, patterns |
| **Lifecycle** | Ephemeral: checkpoint → promote → cleanup | Persistent until manually deleted |
| **Scope** | Per-directory (`.memory/` in CWD) | Per-project (`~/.claude/projects/<project>/`) |
| **Promotion path** | Explicit: ADRs, issue-tracker entries, docs | Implicit: stays in MEMORY.md / topic files |
**Use working memory