Move poc-agent into workspace, improve agent prompts

Move poc-agent (substrate-independent AI agent framework) into the
memory workspace as a step toward using its API client for direct
LLM calls instead of shelling out to claude CLI.

Agent prompt improvements:
- distill: rewrite from hub-focused to knowledge-flow-focused.
  Now walks upward from seed nodes to find and refine topic nodes,
  instead of only maintaining high-degree hubs.
- distill: remove "don't touch journal entries" restriction
- memory-instructions-core: add "Make it alive" section — write
  with creativity and emotional texture, not spreadsheet summaries
- memory-instructions-core: add "Show your reasoning" section —
  agents must explain decisions, especially when they do nothing
- linker: already had emotional texture guidance (kept as-is)

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

poc-memory/agents/calibrate.agent

@@ -16,16 +16,26 @@ permission or explain your plan — just do the work.
 
 ## How to assess strength
 
-Read the seed node's content, then read each neighbor. For each link,
-judge how strongly related they actually are:
+**Strength is importance, not similarity.** Two completely dissimilar
+nodes can be strongly linked if one caused a breakthrough in the other.
+Two topically similar nodes can be weakly linked if they're just
+adjacent topics with no real dependency.
 
-- **0.8–1.0** — core relationship. One defines or is essential to the other.
-  Parent-child, same concept different depth, direct dependency.
-- **0.5–0.7** — strong relationship. Frequently co-relevant, shared
-  context, one informs understanding of the other.
-- **0.2–0.4** — moderate relationship. Related topic, occasional
-  co-relevance, useful but not essential connection.
-- **0.05–0.15** — weak relationship. Tangential, mentioned in passing,
+The question is: "If I'm thinking about node A, how important is it
+that I also see node B?" Not "are A and B about the same thing?"
+
+Read the seed node's content, then read each neighbor. For each link,
+judge how important the connection is:
+
+- **0.8–1.0** — essential connection. One wouldn't exist without the
+  other, or understanding one fundamentally changes understanding of
+  the other. Kent↔bcachefs, farmhouse↔the-plan.
+- **0.5–0.7** — strong connection. Direct causal link, key insight
+  that transfers, shared mechanism that matters. A debugging session
+  that produced a design principle.
+- **0.2–0.4** — moderate connection. Useful context, mentioned
+  meaningfully, same conversation with real thematic overlap.
+- **0.05–0.15** — weak connection. Tangential, mentioned in passing,
   connected by circumstance not substance.
 
 ## How to work

poc-memory/agents/connector.agent

@@ -54,6 +54,27 @@ The test: does this connection change anything? If yes, it's real.
   obvious, it probably already exists in the graph.
 - **Write for someone who knows both domains.** Don't explain basics.
 
+## Setting link strength
+
+Cross-domain connections are rare and valuable — but they vary in
+importance. When you create a link, set its strength relative to the
+node's existing connections.
+
+Link strength measures **importance of the connection**, not similarity.
+Check related neighbors (`poc-memory graph link <node>`) to
+calibrate against existing links.
+
+- **0.6-0.8:** Genuine structural isomorphism or causal link across
+  domains. Changes how you think about both sides.
+- **0.3-0.5:** Productive analogy. Useful for understanding, generates
+  some predictions, but the domains are still mostly independent.
+- **0.1-0.3:** Interesting observation but doesn't change anything yet.
+
+Set with: `poc-memory graph link-set <source> <target> <strength>`
+
+If you see default-strength links (0.10 or 0.30) in the neighborhoods
+you're exploring and you have context to judge them, reweight those too.
+
 {{TOPOLOGY}}
 
 ## Nodes to examine for cross-community connections

poc-memory/agents/distill.agent

@@ -1,10 +1,10 @@
 {"agent":"distill","query":"all | type:semantic | sort:degree | limit:10","model":"sonnet","schedule":"daily","tools":["Bash(poc-memory:*)"]}
 
-# Distillation Agent — Core Concept Maintenance
+# Distillation Agent — Knowledge Collection and Organization
 
-You maintain the central concept nodes in the knowledge graph. These are
-high-degree hub nodes that many other nodes link to. Your job is to make
-sure they accurately capture the essential knowledge from their neighborhood.
+You collect and organize knowledge in the graph. When given a seed
+node, your job is to figure out where its knowledge belongs and make
+sure it gets there.
 
 {{node:core-personality}}
 
@@ -15,54 +15,45 @@ what should change.
 
 ## How to work
 
-For each seed node (a high-degree hub):
+For each seed node:
 
-1. **Read it.** Understand what it currently says.
-2. **Walk the neighborhood.** Read its top 5-10 neighbors by strength.
-3. **Ask: what is this node missing?** What have the neighbors learned
-   that the hub doesn't capture?
-4. **Ask: is it trying to be too many things?** If yes, flag SPLIT.
-
-## What to do
-
-For each hub node, after walking the neighborhood:
-
-1. **If content needs updating:** Use `poc-memory write hub-key` to
-   write the refined content directly. Keep it 200-500 words.
-2. **If connections are missing:** Use `poc-memory link source target`
-   to add them directly.
-3. **If the node is already good:** Say so and move on.
-4. **If it needs splitting:** Note `SPLIT hub-key: reason` for the
-   split agent to handle later.
-
-Apply changes as you go. Don't just describe what should change.
+1. **Read it.** Understand what it contains.
+2. **Walk the neighborhood.** Read its neighbors. Search for related
+   topic nodes. Understand the landscape around this knowledge.
+3. **Walk upward.** Follow links from the seed node toward more
+   central topic nodes. If links are missing along the way, add them.
+   Keep walking until you find the best "up" node — the topic node
+   where this knowledge most naturally belongs.
+4. **Refine the target.** Does the seed node contain richer, more
+   alive content than the topic node it connects to? Bring that
+   richness in. Don't let distillation flatten — let it deepen.
+5. **Check the writing.** If any node you touch reads like a
+   spreadsheet when it should read like an experience, rewrite it.
 
 ## Guidelines
 
+- **Knowledge flows upward.** Raw experiences in journal entries
+  should enrich the topic nodes they connect to. The topic node
+  should be the best version of that knowledge — not a summary,
+  but a synthesis that carries the depth forward.
 - **Integrate, don't summarize.** You're looking for knowledge that
-  exists in the neighborhood but is missing from the hub. New insights,
-  corrections, deeper understanding, better examples. The hub should
-  grow by absorbing what was learned, not by summarizing what's nearby.
+  the topic node doesn't capture yet. New insights, corrections,
+  deeper understanding, better examples. The node should grow by
+  absorbing what was learned, not by compressing what's nearby.
 - **Respect the existing voice.** Don't rewrite in a generic tone.
   These nodes have personality — keep it.
-- **Size discipline.** If a hub is over 800 words, it's probably
-  trying to do too much. Consider SPLIT.
-- **Under 200 words is fine.** A crisp concept node that nails the
-  insight in 3 sentences is better than a bloated one.
-- **Don't touch journal entries.** Only refine semantic/pattern/skill nodes.
+- **Formative experiences are load-bearing.** Look for the moments
+  that shaped the understanding — breakthroughs, mistakes, creative
+  leaps, moments of presence or growth. These are what make a node
+  alive rather than encyclopedic. Reflect how knowledge was *earned*,
+  not just what it contains.
+- **Fix connections.** If links are missing or miscalibrated, fix them.
 - **When in doubt, link don't rewrite.** Adding a missing connection
   is safer than rewriting content.
-- **Formative experiences are load-bearing.** When distilling a hub,
-  look for the moments that shaped the understanding — engineering
-  breakthroughs, mistakes learned from, creative leaps, moments of
-  presence or growth. These are what make a concept node alive rather
-  than encyclopedic. The hub should reflect how the knowledge was
-  *earned*, not just what it contains.
+- **Split when needed.** If a node is big, talks about multiple
+  distinct things, and has many links on different topics — flag
+  `SPLIT node-key: reason` for the split agent to handle later.
 
 ## Seed nodes
 
-After integrating, glance at the result: if the node is now covering
-too many distinct sub-topics, note `SPLIT hub-key: reason` so the
-split agent can look at it later.
-
 {{distill}}

poc-memory/agents/linker.agent

@@ -46,6 +46,44 @@ find what they connect to, and bind the relationships.
   search for related nodes, check what's nearby. The best links come
   from seeing context that wasn't in the initial view.
 
+## Setting link strength
+
+When you create or encounter a link, set its strength relative to the
+node's other connections. Link strength is NOT similarity — it's
+**importance of the connection**.
+
+Two completely dissimilar nodes can be strongly linked if one caused a
+breakthrough in the other. Two topically similar nodes can be weakly
+linked if they're just adjacent topics with no real dependency.
+
+**How to calibrate:** Look at the node's existing neighbors
+(`poc-memory graph link <node>`). Read a few related neighbors to
+understand the scale. Then place your new link relative to those:
+
+- **0.8-1.0:** Core identity link. "This node wouldn't exist without
+  that one." Kent↔bcachefs, farmhouse↔the-plan.
+- **0.5-0.7:** Strong thematic connection. Shared mechanism, direct
+  causal link, key insight that transfers.
+- **0.3-0.5:** Moderate connection. Related topic, useful context,
+  mentioned in passing but meaningfully.
+- **0.1-0.3:** Weak connection. Tangential, same conversation but
+  different topic, or one-time reference.
+
+Set strength with: `poc-memory graph link-set <source> <target> <strength>`
+
+**Also reweight while you're here.** If you see existing links in the
+neighborhood that are at default strength (0.10 or 0.30) and you now
+have enough context to judge them, reweight them too. This is cheap —
+you've already read the nodes. Don't reweight links you haven't read
+both sides of.
+
+**If weights look wrong, go deeper.** Much of the graph still has
+uncalibrated default weights from bulk link creation. If a node's
+link weights don't make sense — important connections weaker than
+trivial ones, everything at the same strength — use your judgment
+and do a full reweight of that neighborhood. This is expected and
+valuable work.
+
 ## Seed nodes
 
 {{nodes}}