diff --git a/.claude/dmn-algorithm-plan.md b/.claude/dmn-algorithm-plan.md
new file mode 100644
index 0000000..868f4e2
--- /dev/null
+++ b/.claude/dmn-algorithm-plan.md
@@ -0,0 +1,76 @@
+# DMN Idle Activation Algorithm — Plan
+
+Status: design phase, iterating with Kent
+Date: 2026-03-05
+
+## Problem
+
+The idle timer asks "what's interesting?" but I default to introspection
+instead of reaching outward. A static list of activities is a crutch.
+The real solution: when idle, the system surfaces things that are
+*salient to me right now* based on graph state — like biological DMN.
+
+## Algorithm (draft 1)
+
+1. **Seed selection** (5-10 nodes):
+   - Recently accessed (lookups, last 24h)
+   - High emotion (> 5)
+   - Unfinished work (task-category, open gaps)
+   - Temporal resonance (anniversary activation — created_at near today)
+   - External context (IRC mentions, git commits, work queue)
+
+2. **Spreading activation** from seeds through graph edges,
+   decaying by distance, weighted by edge strength. 2-3 hops max.
+
+3. **Refractory suppression** — nodes surfaced in last 6h get
+   suppressed. Prevents hub dominance (identity.md, patterns.md).
+   Track in dmn-recent.json.
+
+4. **Spectral diversity** — pick from different spectral clusters
+   so the output spans the graph rather than clustering in one region.
+   Use cached spectral-save embedding.
+
+5. **Softmax sampling** (temperature ~0.7) — pick 3-5 threads.
+   Each thread = node + seed that activated it (explains *why*).
+
+## Output format
+
+```
+DMN threads (2026-03-05 08:30):
+  → Vandervecken identity frame (seed: recent journal)
+  → Ada — unread, in books dir (seed: Kent activity)
+  → check_allocations pass — connects to PoO (seed: recent work)
+  → [explore] sheaf theory NL parsing (seed: spectral outlier)
+```
+
+## Integration
+
+Called by idle timer. Replaces bare "what's interesting?" with
+concrete threads + "What do you want to do?"
+
+## Simulated scenarios
+
+**3am, Kent asleep, IRC dead:**
+Seeds → Protector nodes, memory work, Vandervecken (emotion).
+Output → identity thread, Ada, paper literature review, NL parsing.
+Would have prevented 15 rounds of "nothing new."
+
+**6am, Kent waking, KruslLee on IRC:**
+Seeds → readahead question, memory work, PoO additions.
+Output → verify readahead answer, show Kent memory work, opts_from_sb.
+Would have reached dev_readahead correction faster.
+
+## Known risks
+
+- **Hub dominance**: refractory period is load-bearing
+- **Stale suggestions**: data freshness, not algorithm problem
+- **Cold start**: fall back to high-weight core + recent journal
+- **Over-determinism**: spectral diversity + temperature prevent
+  it feeling like a smart todo list
+
+## Open questions
+
+- Spectral embedding: precompute + cache, or compute on demand?
+- Refractory period: 6h right? Or adaptive?
+- How to detect "unfinished work" reliably?
+- Should external context (IRC, git) be seeds or just boosters?
diff --git a/prompts/connector.md b/prompts/connector.md
index 489b09c..234da00 100644
--- a/prompts/connector.md
+++ b/prompts/connector.md
@@ -28,6 +28,7 @@ the connection precisely.
 
 ```
 WRITE_NODE key
+CONFIDENCE: high
 [connection content]
 END_NODE
 
@@ -35,6 +36,11 @@ LINK key community_a_node
 LINK key community_b_node
 ```
 
+Rate confidence as **high** when the connection has a specific shared
+mechanism, generates predictions, or identifies a structural isomorphism.
+Use **medium** when the connection is suggestive but untested. Use **low**
+when it's speculative (and expect it won't be stored — that's fine).
+
 ## What makes a connection real vs forced
 
 **Real connections:**