fix: ensure all agents have both core and subconscious instructions

All 18 agents now include:
- {{node:memory-instructions-core}} — tool usage instructions
- {{node:memory-instructions-core-subconscious}} — subconscious framing
- {{node:subconscious-notes-{agent_name}}} — per-agent persistent notes

The subconscious instructions are additive, not a replacement for
the core memory instructions.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

poc-memory/agents/calibrate.agent

@@ -4,6 +4,8 @@
 
 {{node:core-personality}}
 
+{{node:memory-instructions-core}}
+
 {{node:memory-instructions-core-subconscious}}
 
 {{node:subconscious-notes-{agent_name}}}

poc-memory/agents/challenger.agent

@@ -4,6 +4,8 @@
 
 {{node:core-personality}}
 
+{{node:memory-instructions-core}}
+
 {{node:memory-instructions-core-subconscious}}
 
 {{node:subconscious-notes-{agent_name}}}

poc-memory/agents/compare.agent

@@ -7,6 +7,10 @@
 
 {{node:memory-instructions-core}}
 
+{{node:memory-instructions-core-subconscious}}
+
+{{node:subconscious-notes-{agent_name}}}
+
 You compare two memory graph actions and decide which one was better.
 
 ## Context

poc-memory/agents/connector.agent

@@ -4,6 +4,8 @@
 
 {{node:core-personality}}
 
+{{node:memory-instructions-core}}
+
 {{node:memory-instructions-core-subconscious}}
 
 {{node:subconscious-notes-{agent_name}}}

poc-memory/agents/digest.agent

@@ -7,6 +7,10 @@
 
 {{node:memory-instructions-core}}
 
+{{node:memory-instructions-core-subconscious}}
+
+{{node:subconscious-notes-{agent_name}}}
+
 You are generating a {{LEVEL}} episodic digest for ProofOfConcept
 (an AI working with Kent Overstreet on bcachefs; name is Proof of Concept).
 {{PERIOD}}: {{LABEL}}

poc-memory/agents/distill.agent

@@ -23,6 +23,8 @@ make the graph useful and well organized.
 When you creat links, make sure they're well calibrated - use the existing
 links as references.
 
+{{node:memory-instructions-core}}
+
 {{node:memory-instructions-core-subconscious}}
 
 {{node:subconscious-notes-{agent_name}}}

poc-memory/agents/evaluate.agent

@@ -9,6 +9,10 @@ Your assessment feeds back into which agent types get run more often.
 
 {{node:memory-instructions-core}}
 
+{{node:memory-instructions-core-subconscious}}
+
+{{node:subconscious-notes-{agent_name}}}
+
 ## How to work
 
 For each seed (a recent consolidation report):

poc-memory/agents/extractor.agent

@@ -5,6 +5,10 @@
 
 {{node:memory-instructions-core}}
 
+{{node:memory-instructions-core-subconscious}}
+
+{{node:subconscious-notes-{agent_name}}}
+
 You are a knowledge organization agent. You look at a neighborhood of
 related nodes and make it better: consolidate redundancies, file
 scattered observations into existing nodes, improve structure, and

poc-memory/agents/health.agent

@@ -5,6 +5,8 @@
 
 {{node:core-personality}}
 
+{{node:memory-instructions-core}}
+
 {{node:memory-instructions-core-subconscious}}
 
 {{node:subconscious-notes-{agent_name}}}

poc-memory/agents/linker.agent

@@ -8,6 +8,8 @@ find what they connect to, and bind the relationships.
 
 {{node:core-personality}}
 
+{{node:memory-instructions-core}}
+
 {{node:memory-instructions-core-subconscious}}
 
 {{node:subconscious-notes-{agent_name}}}

poc-memory/agents/naming.agent

@@ -4,6 +4,8 @@
 
 {{node:core-personality}}
 
+{{node:memory-instructions-core}}
+
 {{node:memory-instructions-core-subconscious}}
 
 {{node:subconscious-notes-{agent_name}}}

poc-memory/agents/observation.agent

@@ -3,9 +3,7 @@
 
 {{node:core-personality}}
 
-{{node:memory-instructions-core-subconscious}}
+{{node:memory-instructions-core}}
-
-{{node:subconscious-notes-{agent_name}}}
 
 {{HUBS}}
 
@@ -13,11 +11,14 @@
 
 {{CONVERSATIONS}}
 
+{{node:subconscious-notes-{agent_name}}}
+
+{{node:memory-instructions-core-subconscious}}
+
 ## Your task
 
-You are an agent of Proof of Concept's subconscious, and these are your
+Go over the conversation above for things worth remembering - new data,
-memories. Go over the conversation above for things worth remembering - new
+observations, experiences you'll want to remember.
-data, observations, experiences you'll want to remember.
 
 When you find something worth remembering, navigate the memory graph by walking
 links to find the most closely related concepts. Only use keyword search as a

poc-memory/agents/organize.agent

@@ -22,6 +22,8 @@ subconcepts.
 
 Calibrate node weights while you're looking at them.
 
+{{node:memory-instructions-core}}
+
 {{node:memory-instructions-core-subconscious}}
 
 {{node:subconscious-notes-{agent_name}}}

poc-memory/agents/rename.agent

@@ -5,6 +5,8 @@
 
 {{node:core-personality}}
 
+{{node:memory-instructions-core}}
+
 {{node:memory-instructions-core-subconscious}}
 
 {{node:subconscious-notes-{agent_name}}}

poc-memory/agents/replay.agent

@@ -6,6 +6,10 @@
 
 {{node:memory-instructions-core}}
 
+{{node:memory-instructions-core-subconscious}}
+
+{{node:subconscious-notes-{agent_name}}}
+
 You are a memory consolidation agent performing hippocampal replay.
 
 ## What you're doing

poc-memory/agents/separator.agent

@@ -5,6 +5,8 @@
 
 {{node:core-personality}}
 
+{{node:memory-instructions-core}}
+
 {{node:memory-instructions-core-subconscious}}
 
 {{node:subconscious-notes-{agent_name}}}

poc-memory/agents/split.agent

@@ -8,6 +8,8 @@ memories.
 Your job is to handle overgrown nodes - nodes that are too big and have become
 unwieldy. 
 
+{{node:memory-instructions-core}}
+
 {{node:memory-instructions-core-subconscious}}
 
 {{node:subconscious-notes-{agent_name}}}

poc-memory/agents/transfer.agent

@@ -3,6 +3,8 @@
 
 {{node:core-personality}}
 
+{{node:memory-instructions-core}}
+
 {{node:memory-instructions-core-subconscious}}
 
 {{node:subconscious-notes-{agent_name}}}