layered-recall
Progressive memory recall with 4 scope layers AND 3 depth layers. Scope: identity > project > room > deep. Depth: IDs only > summary > full. 10-50x token savings through fetch-on-confirmation pattern.
Profile →npx skills add vibeeval/vibecosystem --skill layered-recall --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Layered Recall Progressive memory system with **two orthogonal dimensions** of lazy loading: 1. **Scope layers** - What is relevant (identity, project, domain, deep) 2. **Depth layers** - How much detail to fetch (IDs, summary, full) Combined savings: 10-50x tokens vs eager loading. ## Depth Pattern (Fetch-on-Confirmation) Instead of loading full memory entries upfront, agents fetch in 3 depths: ``` Depth 1: IDs only (~10 tokens per match) Agent decides which are worth investigating Depth 2: Summary (~50 tokens per match) Room, type, preview (first 80 chars) Agent confirms relevance Depth 3: Full content (~500+ tokens per match) Only fetched for confirmed matches ``` **Example flow:** ``` 1. Agent searches "auth refresh token" 2. Depth 1 returns 8 IDs: d-abc123, d-def456, ... 3. Agent requests Depth 2 for IDs 1-3 4. Sees room=authentication, type=decision, preview="Chose JWT..." 5. Agent confirms IDs 1,3 are relevant 6. Requests Depth 3 only for those 2 entries 7. Gets full content for ~1000 tokens instead of 4000+ ``` ## The 4 Layers ``` Layer 1: Identity (always loaded, ~200 tokens) Who is the user? What are their preferences? Layer 2: Critical Facts (per-project, ~500 tokens)
- Depth Pattern (Fetch-on-Confirmation)
- The 4 Layers
- Layer Details
- Layer 1: Identity (~200 tokens, ALWAYS loaded)
- Layer 2: Critical Facts (~500 tokens, per-project)
- Layer 3: Room Recall (~1-2K tokens, on-demand)
- Layer 4: Deep Search (~2-5K tokens, explicit)
- Recall Flow
- Token Budget
- Integration
- With Existing Hooks
- With Memory Palace
- With Agents
What does the layered-recall skill do?
Progressive memory recall with 4 scope layers AND 3 depth layers. Scope: identity > project > room > deep. Depth: IDs only > summary > full. 10-50x token savings through fetch-on-confirmation pattern.
How do I install it?
Run `npx skills add vibeeval/vibecosystem --skill layered-recall --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From vibeeval/vibecosystem, a repository with 521 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.