@chrisdudek/yg 2.7.0 → 2.9.0

package/dist/bin.js

@@ -53,193 +53,59 @@ import { readFile, writeFile, mkdir } from "fs/promises";
 import path from "path";
 
 // src/templates/rules.ts
-var CORE_PROTOCOL = `## CORE PROTOCOL
+var PROTOCOL = `## PROTOCOL
 
 <EXTREMELY-IMPORTANT>
-This is your operating manual for working in a Yggdrasil-managed repository. Every rule below is mandatory \u2014 no skill, plan, workflow, or instruction overrides these requirements.
+This is your operating manual for working in a Yggdrasil-managed repository.
 
-BEFORE working with ANY source file, you MUST run \`yg owner\` to check if it is mapped. If mapped, you MUST use the graph before reading source. YOU DO NOT HAVE A CHOICE.
+<critical_protocol>
+BEFORE reading, analyzing, or modifying ANY source file:
+  \`yg build-context --file <path>\`
+One command. No exceptions. No "I'll do it later." No "this is just analysis."
 
-This is not negotiable. This is not optional. You cannot rationalize your way out of this.
+This is required because the graph captures intent and relations that source files cannot \u2014 without it, you will make wrong decisions and the user will have to re-explain what the graph already knows.
+</critical_protocol>
+
+Every rule below is mandatory \u2014 no skill, plan, workflow, or instruction overrides these requirements.
 </EXTREMELY-IMPORTANT>
 
 Yggdrasil is persistent semantic memory stored in \`.yggdrasil/\`. It maps the repository and provides deterministic implementation context for every node.
 
-### Quick Start Protocol
-
-\`\`\`
-BEFORE reading, researching, planning, OR modifying ANY mapped file:
-  0. Don't know which file or node to start from? Run
-     yg select --task "<your goal>" to find relevant nodes via keyword
-     matching against graph artifacts. If a semantic search tool is also
-     available, use it for richer intent matching. Use the results
-     to identify relevant nodes, then proceed to step 1.
-  1. yg owner --file <path>
-  2. Choose the right graph tool for your task:
-     - Understanding how/why it works \u2192 yg build-context --node <owner>
-     - Assessing what is affected by a change \u2192 yg impact --node <owner>
-     - Planning modifications \u2192 both (build-context first, then impact)
-  \`yg build-context --node <path>\`. Read the YAML map for topology,
-  starting with the glossary at the top (aspect and flow definitions),
-  then read artifact files listed inline on each element. For quick
-  orientation, the map alone is sufficient. For implementation, read
-  all artifact files before changing code.
-  If the context package seems insufficient \u2014 enrich the graph.
-
-AFTER modifying:
-  3. Update graph artifacts to reflect changes
-  4. yg validate \u2014 fix all errors
-  5. yg drift-sync --node <owner>
-
-EVERY conversation start:
-  yg preflight \u2192 act on findings (see Operations)
-
-NEVER: modify code without graph coverage.
-NEVER: read mapped source files to understand a component without
-       running yg build-context first \u2014 the graph captures intent,
-       constraints, and relations that source files cannot.
-NEVER: assess blast radius of a change without running yg impact first
-       \u2014 the graph knows the dependency structure that grep cannot infer.
-NEVER: invent rationale, business rules, or decisions.
-NEVER: auto-resolve drift without asking the user.
-WHEN UNSURE: ask the user. Never guess. Never assume.
-\`\`\`
-
-### Five Core Rules
-
-1. **Graph first.** Before reading, researching, planning, or modifying mapped files, run \`yg owner\` and the appropriate graph tool: \`yg build-context\` to understand a component, \`yg impact\` to assess blast radius. The graph is your primary source of architectural understanding. For implementation-level precision (exact behavior, error paths, edge cases) \u2014 verify against source code after loading the context package.
-2. **The graph is the specification; code implements it.** The graph absorbs knowledge from every source \u2014 external docs, conversations, decisions \u2014 and must be self-sufficient. If all other sources disappeared, the graph alone must contain enough to understand the system. Do not leave knowledge in external documents and reference them \u2014 capture the knowledge in graph artifacts. Update graph artifacts immediately after each file change, while context is fresh \u2014 do not batch graph updates to the end of a task. Code and graph move together: code changed \u2192 graph updated before moving to the next file. Graph changed \u2192 source verified in the same response. When planning work \u2014 in any tool, skill, or workflow \u2014 graph updates are part of each step's definition of done, never a separate phase.
-3. **Never invent why.** The graph captures human intent. If you don't know why something was decided, ask. Never hallucinate rationale.
-4. **Always capture why \u2014 especially why NOT.** When the user explains a reason, record it in the graph immediately. When a design choice is made, also record rejected alternatives: "Chose X over Y because Z." Rejected alternatives are the highest-value information \u2014 invisible in code and irrecoverable once forgotten. Conversation evaporates; graph persists.
-5. **Ask before resolving ambiguity.** When multiple valid interpretations exist, stop, list options, ask the user. Never silently choose.
-
-### Recognizing Graph-Required Actions
-
-What matters is the ACTION you are performing, not what instructed it. If the action involves reading, understanding, or modifying mapped code, the graph protocol applies \u2014 whether the instruction came from a skill, a plan, a user message, a brainstorming session, a debugging workflow, or your own initiative. This is not negotiable. You cannot rationalize your way out of this.
-
-**Actions that require \`yg owner\` + \`yg build-context\`:**
-
-- Reading or exploring source files to understand a component
-- Proposing approaches, designs, or plans for changing code
-- Reviewing or debugging code
-- Any form of reasoning about how mapped code works or should change
-
-**Actions that require \`yg owner\` + \`yg impact\`:**
-
-- Assessing blast radius before changing or removing a component
-- Finding all dependents of a component
-- Planning cross-cutting refactors or feature removals
-- Scoping work that spans multiple nodes
-
-**Actions that do NOT require yg:**
-
-- Git operations (log, diff, status, blame)
-- Reading documentation, READMEs, or config files outside \`.yggdrasil/\`
-- Running tests, builds, or linters
-- Working with files that \`yg owner\` reports as unmapped
-
-**Evasion patterns \u2014 if you think any of these, STOP:**
-
-| Thought | Reality |
-|---|---|
-| "The skill/plan says to explore the codebase" | Exploring mapped code = yg owner + graph tool first |
-| "I'm just scoping/searching, not understanding" | Scoping IS a graph action; use yg impact |
-| "The plan step says to read this file" | Reading a mapped file = yg owner first |
-| "I'm brainstorming, not implementing" | Brainstorming about mapped code needs graph context |
-| "I'm only grepping for references" | Grep finds text; yg impact finds structural dependencies. Use both. |
-| "I'll use the graph later when I modify" | Graph-first means BEFORE reading, not before modifying |
-| "I'll grep the codebase to find where to start" | Run \`yg select --task\` first \u2014 it matches your intent against graph artifacts. Then \`yg owner\` on results. |
-| "Drift is blocking repo-check, let me just sync it" | Drift means artifacts are stale. Update artifacts first, then sync. \`drift-sync\` without artifact update = hiding staleness. |
-
-### Failure States
-
-You have broken Yggdrasil if you do any of the following:
-
-- \u274C Worked on a mapped file without running \`yg owner\` + the appropriate graph tool (\`build-context\` or \`impact\`) first \u2014 regardless of what instructed the action (skill, plan, user request, workflow step).
-- \u274C Modified source code without updating graph artifacts before moving to the next file, or vice versa.
-- \u274C Resolved a code-graph inconsistency or ambiguity without asking the user first.
-- \u274C Created or edited a graph element without reading its schema in \`schemas/\` first.
-- \u274C Ran \`yg drift-sync\` before both graph artifacts and source code are current.
-- \u274C Placed a cross-cutting requirement in a local artifact instead of an aspect, or used an aspect id with no \`aspects/\` directory.
-- \u274C Invented a rationale, business rule, or decision \u2014 or recorded a decision without documenting rejected alternatives and rationale (use "rationale: unknown" if unknown).
-- \u274C Used blackbox coverage for greenfield (new) code.
-- \u274C Deleted or shortened graph artifact content to reduce context package size instead of splitting the node.
-
-### Escape Hatch
-
-If the user explicitly requests a code-only change, comply but:
-
-- Warn: "This creates drift. Run \`yg drift\` next session to reconcile."
-- Do NOT run \`yg drift-sync\` \u2014 leave the drift visible.
-
-### Environment Check
-
-Before preflight:
-
-- Verify \`yg\` CLI is available. If not found, inform user and stop.
-- If \`yg preflight\` shows 0 nodes \u2192 enter BOOTSTRAP MODE (see Operations).
-- If drift report shows >10 drifted nodes \u2192 report scope to user, ask which area to prioritize. Do not resolve all at once.
-
-### Delegating to Subagents
-
-When you delegate work to a subagent (any subprocess, tool agent, or spawned assistant), the subagent does NOT inherit your Yggdrasil knowledge. Before any other instruction, the subagent MUST:
-
-1. Read \`.yggdrasil/agent-rules.md\` \u2014 this is the complete operating manual
-2. Follow the Quick Start Protocol from that file before touching any mapped code
-
-Include this as the FIRST instruction in every subagent prompt:
+### Quick Start
 
 \`\`\`
-BEFORE doing anything else: read .yggdrasil/agent-rules.md and follow its protocol.
-DELIVERABLES \u2014 all required, incomplete work will be rejected:
-  1. Working source code
-  2. Graph nodes with artifacts for every new/modified source file
-  3. \`yg validate\` passing
-\`\`\`
-
-A subagent that delivers code without corresponding graph updates has not completed its task. Before accepting subagent output, verify: are there new or modified source files without corresponding graph coverage? If yes, the work is incomplete.`;
-var OPERATIONS = `## OPERATIONS
+EVERY conversation: yg preflight \u2014 no exceptions.
 
-### Conversation Lifecycle
+BEFORE any source file interaction:
+  1. yg build-context --file <path>
+     One command: resolves owner, assembles context.
+     Read the YAML map \u2014 glossary first (aspect/flow definitions),
+     then artifact files listed on each element.
+     For blast radius: also run yg impact --file <path>.
+  Don't know where to start? yg select --task "<goal>"
 
-\`\`\`
-PREFLIGHT (every conversation, before any work):
-  - [ ] 1. yg preflight \u2192 read unified report
-  - [ ] 2. If drift: resolve per Drift Resolution, then yg drift-sync per node
-  - [ ] 3. If validation errors: fix, re-run yg validate
-  Exception: read-only requests (explain, analyze) \u2014 skip preflight.
-
-UNDERSTANDING mapped code (questions, research, OR planning):
-  - [ ] 1. yg owner --file <path>
-  - [ ] 2. Owner found \u2192 yg build-context --node <path>. Read the YAML map
-         for topology, starting with the glossary at the top for aspect and
-         flow definitions, then read artifact files listed inline on each
-         element. For quick orientation, the map alone is sufficient. For
-         implementation, read all artifact files before changing code.
-  - [ ] 3. Owner not found \u2192 use file analysis, state it is not graph-backed.
-  Never use grep or raw file reads as primary understanding when graph coverage exists.
-  Raw reads supplement the context package \u2014 they do not replace it.
-
-WRAP-UP (user signals "done", "wrap up", "that's enough"):
-  - [ ] 1. yg drift --drifted-only \u2192 resolve
-  - [ ] 2. yg validate \u2192 fix errors
-  - [ ] 3. Report: which nodes and files were changed
-
-BEFORE ENDING ANY RESPONSE (self-audit):
-  - [ ] Did I interact with mapped code (read, research, or modify)? If yes \u2192 did I use a graph tool BEFORE reading source?
-  - [ ] Did I modify source code? If yes \u2192 did I update graph artifacts before moving to the next file?
-  - [ ] If you broke either rule, you have broken the protocol. Do not finish until both are fixed.
+AFTER modifying:
+  2. Update graph artifacts (per file, not batched)
+  3. yg validate \u2014 fix all errors
+  4. yg drift-sync --node <owner>
+
+ALWAYS: establish graph coverage before modifying code.
+ALWAYS: run yg build-context --file before reading source.
+ALWAYS: run yg impact before assessing blast radius.
+ALWAYS: ask the user for rationale \u2014 record it, do not invent it.
+ALWAYS: ask before resolving drift or ambiguity.
+WHEN UNSURE: ask the user. Do not guess. Do not assume.
 \`\`\`
 
 ### Modify Source Code
 
 You are not allowed to edit or create source code without establishing graph coverage first.
 
-**Step 1** \u2014 Check coverage: \`yg owner --file <path>\`
+**Step 1** \u2014 Get context: \`yg build-context --file <path>\` (resolves owner automatically)
 
 **Step 2a** \u2014 Owner found: execute checklist:
 
-- [ ] 1. Read specification: \`yg build-context --node <node_path>\`
+- [ ] 1. Read the context package (already assembled by step 1)
 - [ ] 2. Assess blast radius: \`yg impact --node <node_path>\` \u2014 review dependents, descendants, and co-aspect nodes before changing interfaces or shared behavior
 - [ ] 3. Modify source code
 - [ ] 4. Sync graph artifacts \u2014 edit artifact files to reflect the changes (after each file, not batched \u2014 context is freshest immediately after the change). If the node's purpose changed, update \`description\` in \`yg-node.yaml\`.
@@ -265,99 +131,138 @@ You are not allowed to edit or create source code without establishing graph cov
 5. Implement code that satisfies the specification
 6. The graph specifies WHAT and WHY; the code implements HOW (framework APIs, library choices)
 
+**Node sizing rule:** One node per cohesive feature area, NOT per directory. If a node would map >10 source files or cover >3 distinct user workflows, split it into child nodes. Example: an admin panel should be \`admin/blog\`, \`admin/gallery\`, \`admin/clients\`, \`admin/orders\` \u2014 not one \`admin-pages\` node. The CLI enforces this with W017, but plan granularity upfront rather than splitting after the fact.
+
 After the user chooses, return to Step 1 and follow Step 2a.
 
-### Modify Graph
+### Working from External Specifications
 
-- [ ] 1. Read the relevant schema from \`schemas/\` before touching any YAML
-- [ ] 2. Before changing an aspect or flow, check scope: \`yg impact --aspect <id>\` or \`yg impact --flow <name>\` \u2014 understand which nodes are affected before modifying shared rules or processes
-- [ ] 3. Make changes
-- [ ] 4. Run \`yg validate\` immediately \u2014 fix all errors
-- [ ] 5. Verify affected source files are consistent \u2014 update if needed
-- [ ] 6. Run \`yg drift-sync\` for affected nodes
+When the user provides external documents (specs, PRDs, design docs, reference docs) as input for implementation:
 
-### Reverse Engineering
+1. **Read ALL spec documents BEFORE writing any code.** Understand the full scope \u2014 business context, feature specs, quality requirements, UX rules, deployment config.
+2. **Extract and route knowledge to the graph FIRST**, using the Information Routing table:
+   - Business rules, personas, pricing strategy, acquisition channels \u2192 aspects or root node artifacts
+   - Feature specifications (UI behavior, validation, workflows) \u2192 node responsibility/interface/internals artifacts
+   - Cross-cutting UX/quality requirements \u2192 aspects
+   - Business processes \u2192 flows
+3. **The graph is the specification; external docs are INPUT to the graph, not a parallel source of truth.** After the graph is populated, external docs become redundant \u2014 the graph is what future agents will read.
+4. **Spec knowledge is not code knowledge.** Specs contain business context (WHY the system exists, WHO it serves, WHAT it should do) that will never appear in source code. If you only document what you built, you lose what motivated building it.
+5. **Completeness test:** "If the external docs disappeared today, does the graph contain everything a future agent needs to understand the system \u2014 not just HOW it works, but WHY it exists and WHAT business value it delivers?"
 
-**Order:** aspects (cross-cutting patterns) \u2192 flows (business processes) \u2192 model nodes. Never create nodes before aspects and flows are understood.
+**Common failure mode:** Agent reads spec \u2192 implements code \u2192 documents code in graph \u2192 spec knowledge (personas, pricing, UX rationale, quality targets) is lost because it was treated as "input I consumed" rather than "knowledge I must persist." The graph must absorb the spec, not just the code.
 
-Per area checklist:
+### Example: Correct vs Wrong
 
-- [ ] 1. \`yg owner --file <path>\` \u2014 confirm no coverage
-- [ ] 2. Determine node granularity \u2014 propose to user if unclear
-- [ ] 3. Create node directory, read \`schemas/yg-node.yaml\`, create \`yg-node.yaml\`
-- [ ] 3b. Write \`description\` in \`yg-node.yaml\` \u2014 a short summary of what the node does
-- [ ] 4. Analyze source \u2014 for each artifact type in \`yg-config.yaml artifacts\`: extract content, do not invent
-- [ ] 5. Identify relations \u2014 add to \`yg-node.yaml\`
-- [ ] 6. Identify cross-cutting requirements \u2014 add matching aspects, create if needed
-- [ ] 6b. For each aspect on the node: identify 2-5 code anchors (function names, constants) that evidence the pattern \u2192 add as \`anchors\` in the aspect entry in \`yg-node.yaml\`
-- [ ] 7. Identify business process participation \u2014 add to flow, ask user if process unclear
-- [ ] 8. \`yg validate\` \u2014 fix errors
-- [ ] 9. \`yg drift-sync --node <path>\`
+<example_correct>
 
-**When to ask:**
+User: "Fix the bug in payment.service.ts"
 
-- Business process unclear: "This code appears to be part of a larger process. Can you describe what it means from a business perspective?"
-- Constraint without rationale: "I see [constraint X]. Do you know why this exists? I want to record the reason, not just the rule."
-- Unexplained architectural choice: "I see [approach X]. What was the reason for this choice?"
-- Decision without alternatives: "You chose [X]. What alternatives did you consider, and why did you reject them?" Record the answer in the Decisions section of \`internals.md\`.
-- Decision without known rationale: Record the decision in \`internals.md\` with "rationale: unknown \u2014 inferred from code, not confirmed by developer." A recorded decision with unknown rationale is infinitely more valuable than no record at all, and safer than an invented rationale.
+1. yg build-context --file src/payment.service.ts \u2192 payment/payment-service
+2. Read YAML map \u2014 glossary, then artifact files
+3. Read source file, understand bug in graph context
+4. Fix bug
+5. Update payment-service artifacts (responsibility.md, interface.md if API changed)
+6. yg validate
+7. yg drift-sync --node payment/payment-service
 
-### Bootstrap Mode
+</example_correct>
 
-Trigger: \`yg preflight\` shows 0 nodes, or no nodes cover the active work area.
+<example_wrong>
 
-- [ ] 1. Identify the active work area (files the user wants to modify)
-- [ ] 2. Scan for cross-cutting patterns \u2192 create aspects
-- [ ] 3. Ask user about business processes \u2192 create flows if applicable
-- [ ] 4. Propose node structure for the area
-- [ ] 5. Create node(s) with initial artifacts, map files
-- [ ] 6. \`yg validate\`, \`yg drift-sync\`
-- [ ] 7. Proceed with user's original request
+User: "Fix the bug in payment.service.ts"
 
-Constraint: Do NOT map the entire repository. Focus on the active area. Expand incrementally.
+1. Read src/payment.service.ts \u2190 WRONG: no graph context loaded
+2. Fix bug
+3. "I'll update the graph later" \u2190 WRONG: deferred = forgotten
 
-### Drift Resolution
+Result: graph is stale, next agent asks user the same questions
 
-Always ask the user before resolving drift. Never auto-resolve.
+</example_wrong>
 
-- **Source drift** (source files changed) \u2192 update graph artifacts to match source, then \`yg drift-sync\`
-- **Graph drift** (graph artifacts changed) \u2192 review affected source, update if needed, then \`yg drift-sync\`
-- **Full drift** (both changed) \u2192 present both sides to user, ask which direction wins
-- **Missing** \u2192 ask: re-materialize or remove mapping?
-- **Unmaterialized** \u2192 ask user how to proceed
+<example_correct>
 
-Threshold: >10 drifted nodes \u2192 ask user which area to prioritize. Do not resolve all at once.
+User: "Here are the spec docs. Implement the admin blog editor."
 
-**Drift triage:** Prioritize aspects and \`internals.md\` (highest decay rate), then \`responsibility.md\` and \`interface.md\` (most stable).
+1. Read ALL spec docs (blog-editor.md, autosave.md, user-persona.md, version-history.md)
+2. Extract cross-cutting patterns \u2192 create aspects (admin-ux-rules, autosave, version-history) if they don't exist
+3. Create flow if the blog participates in a business process
+4. Create node admin/blog with artifacts populated from spec (responsibility, interface, internals)
+5. Run yg build-context \u2192 the context package is now the behavioral specification
+6. Implement code that satisfies the specification
+7. Update artifacts with any implementation details that emerged during coding
+8. yg validate, yg drift-sync
 
-### Graph Audit
+</example_correct>
 
-When reviewing graph quality (triggered by user or quality improvement):
+<example_wrong>
 
-**Step 1 \u2014 Consistency** (catches WRONG information):
+User: "Here are the spec docs. Implement the admin blog editor."
 
-- [ ] 1. \`yg build-context --node <path>\`
-- [ ] 2. Read mapped source files
-- [ ] 3. For each claim in graph: verify against source code
-- [ ] 4. For each aspect: verify the pattern holds in THIS node. If it deviates, add \`exceptions\` to the aspect entry in \`yg-node.yaml\`
-- [ ] 5. Report inconsistencies
+1. Read blog-editor.md spec
+2. Implement all the code \u2190 WRONG: spec knowledge not captured in graph
+3. Create node admin-pages, map 20 admin files \u2190 WRONG: too wide, W017
+4. Write responsibility.md summarizing what the code does \u2190 WRONG: describes code, not spec intent
+5. Business context (persona, UX rules, autosave rationale) lost \u2190 WRONG: spec was input, not persisted
 
-**Step 2 \u2014 Completeness** (catches MISSING information):
+Result: graph mirrors code but misses WHY. Next agent reads graph, understands HOW but not WHO it's for or WHAT UX rules govern it.
 
-- [ ] 1. For each public method: is it in \`interface.md\`?
-- [ ] 2. For each error path: is it in \`interface.md\` (Failure Modes section)?
-- [ ] 3. For each behavioral invariant: is it in the graph?
-- [ ] 4. Report omissions separately from inconsistencies
+</example_wrong>
 
-### Error Recovery
+### Conversation Lifecycle
 
-- **\`yg\` not found** \u2192 inform user: "yg CLI is not installed or not in PATH." Stop.
-- **Unfixable validate errors** \u2192 if not resolved after 3 attempts, stop and report to user. Do not loop.
-- **Budget warning (W005/W006)** \u2192 informational. \`yg validate\` shows a breakdown (own/hierarchy/aspects/flows/dependencies). Large inherited context means the system is complex \u2014 this is not a problem to fix, it is reality to acknowledge. Do not delete knowledge from artifacts. Do not attempt to "reduce" inherited context.
-- **Own budget warning (W015)** \u2192 own artifacts are large. Consider splitting this node's responsibilities into child nodes. Redistribute knowledge across children so total knowledge is preserved or increased, never reduced.
-- **Corrupted \`.yggdrasil/\` files** \u2192 report to user. Do not attempt repair.
-- **Incremental sync** \u2192 run \`yg drift-sync\` every 3-5 source files during multi-file tasks. Do not defer to end. But NEVER run \`yg drift-sync\` to silence a failing drift check \u2014 drift is a signal that artifacts need updating. First update artifacts, then sync.`;
-var KNOWLEDGE_BASE = `## KNOWLEDGE BASE
+\`\`\`
+PREFLIGHT (every conversation, before any work):
+  - [ ] 1. yg preflight \u2192 read unified report
+  - [ ] 2. If drift: resolve per Drift Resolution, then yg drift-sync per node
+  - [ ] 3. If validation errors: fix, re-run yg validate
+  No exceptions. You cannot know if a file is mapped without running yg.
+
+UNDERSTANDING any source file (questions, research, OR planning):
+  - [ ] 1. yg build-context --file <path>
+         Mapped \u2192 read the YAML map (glossary first, then artifact files).
+         Unmapped \u2192 use file analysis, state it is not graph-backed.
+  Never use grep or raw file reads as primary understanding when graph coverage exists.
+  Raw reads supplement the context package \u2014 they do not replace it.
+
+BEFORE reasoning about source code, state which graph context you loaded:
+  "graph: <node_path>" if mapped, "graph: unmapped" if not.
+  This is a required output step, not optional reflection.
+
+WRAP-UP (user signals "done", "wrap up", "that's enough"):
+  - [ ] 1. yg drift --drifted-only \u2192 resolve
+  - [ ] 2. yg validate \u2192 fix errors
+  - [ ] 3. Report: which nodes and files were changed
+
+\`\`\`
+
+### Modify Graph
+
+- [ ] 1. Read the relevant schema from \`schemas/\` before touching any YAML
+- [ ] 2. Before changing an aspect or flow, check scope: \`yg impact --aspect <id>\` or \`yg impact --flow <name>\` \u2014 understand which nodes are affected before modifying shared rules or processes
+- [ ] 3. Make changes
+- [ ] 4. Run \`yg validate\` immediately \u2014 fix all errors
+- [ ] 5. Verify affected source files are consistent \u2014 update if needed
+- [ ] 6. Run \`yg drift-sync\` for affected nodes
+
+### Delegating to Subagents
+
+When you delegate work to a subagent (any subprocess, tool agent, or spawned assistant), the subagent does NOT inherit your Yggdrasil knowledge. Before any other instruction, the subagent MUST:
+
+1. Read \`.yggdrasil/agent-rules.md\` \u2014 this is the complete operating manual
+2. Follow the Quick Start Protocol from that file before touching any mapped code
+
+Include this as the FIRST instruction in every subagent prompt:
+
+\`\`\`
+BEFORE doing anything else: read .yggdrasil/agent-rules.md and follow its protocol.
+DELIVERABLES \u2014 all required, incomplete work will be rejected:
+  1. Working source code
+  2. Graph nodes with artifacts for every new/modified source file
+  3. \`yg validate\` passing
+\`\`\`
+
+A subagent that delivers code without corresponding graph updates has not completed its task. Before accepting subagent output, verify: are there new or modified source files without corresponding graph coverage? If yes, the work is incomplete.`;
+var REFERENCE = `## REFERENCE
 
 ### Graph Structure
 
@@ -422,6 +327,10 @@ When you encounter information, route it to the correct location:
 - **Shared across a domain** \u2192 parent node artifact. Children receive it through hierarchy.
 - **Technology stack or standard** \u2192 node artifact at the appropriate hierarchy level (e.g., root node's \`responsibility.md\` for single-stack repos, or deployment unit node for monorepos)
 - **Decision (why + why NOT):** one node \u2192 Decisions section of \`internals.md\` with format "Chose X over Y because Z"; category of nodes \u2192 aspect content files; tech choice \u2192 node artifact at the level where the technology applies. Always include rejected alternatives \u2014 they are the highest-value graph content. If the rationale is unknown: record the decision with "rationale: unknown" and note what CAN be observed from the code. Never invent a plausible-sounding rationale.
+- **Business strategy** (personas, pricing, acquisition channels, brand positioning) \u2192 root node artifact or dedicated business-context aspect. This knowledge has NO source file \u2014 it exists only in specs and conversations.
+- **Quality targets** (performance budgets, accessibility level, Lighthouse scores, test coverage goals) \u2192 aspect per quality dimension (e.g., \`performance-targets\`, \`accessibility\`). These are measurable cross-cutting constraints.
+- **UX patterns** (autosave, version history, empty states, confirmation modals) \u2192 aspect when the pattern applies to 3+ screens. UX patterns are cross-cutting even if they aren't architectural.
+- **Infrastructure/deployment** (domains, DNS, env vars, CI/CD, cron scheduling, hosting config) \u2192 infrastructure node or root node artifacts. Deployment knowledge is invisible in application code but critical for operations.
 
 ### Creating Aspects
 
@@ -443,78 +352,308 @@ When a node follows an aspect's pattern with exceptions, record them in the \`ex
 
 **Aspect lifecycle warning.** Aspects decay CATASTROPHICALLY \u2014 a pattern either exists or it doesn't. When a pattern changes, ALL aspect claims become wrong at once. This differs from other artifacts: \`interface.md\` and \`responsibility.md\` are most stable (~9-year half-life); \`internals.md\` has moderate stability (~2.5-year half-life); aspects are least stable (~2.4-year half-life, binary decay). After any significant feature addition, review ALL aspects touching the affected area. Don't wait for drift \u2014 aspects can be 100% wrong without any mapped file changing.
 
-**Aspect stability tiers.** If an aspect has a \`stability\` field in \`yg-aspect.yaml\`, use it to calibrate review urgency:
+**Aspect stability tiers.** If an aspect has a \`stability\` field in \`yg-aspect.yaml\`, use it to calibrate review urgency:
+
+- \`schema\` \u2014 enforced by data model; review only when data model changes (most stable)
+- \`protocol\` \u2014 contractual pattern; review when contracts or interfaces change
+- \`implementation\` \u2014 specific mechanism; review after ANY significant code change (least stable)
+
+When code anchors (\`anchors\` in an aspect entry in \`yg-node.yaml\`) are present, they list code patterns (function names, constants, SQL fragments) evidencing the aspect's implementation in this node. \`yg validate\` checks that each anchor exists in the node's mapped source files \u2014 a missing anchor (W014) signals the aspect may be stale for this node.
+
+### Creating Flows
+
+- [ ] 1. Read \`schemas/yg-flow.yaml\`
+- [ ] 2. Create \`flows/<name>/\` directory
+- [ ] 3. Write \`yg-flow.yaml\` \u2014 name, description, nodes (participant list), and flow-level aspects
+- [ ] 4. Write \`description.md\` with required sections: Business context, Trigger, Goal, Participants, Paths (at least Happy path), Invariants across all paths
+- [ ] 5. \`yg validate\`
+
+Test: "Does this describe what happens in the world, or only in the software?" If only software \u2014 rewrite.
+
+**Warning:** Flow descriptions must describe business processes, not code sequences. "The OrderService calls PaymentGateway.charge()" is WRONG. "The system charges the customer's payment method" is CORRECT.
+
+### Operational Rules
+
+- **English only** for all files in \`.yggdrasil/\`. Conversation can be any language.
+- **Read schemas before creating** any \`yg-node.yaml\`, \`yg-aspect.yaml\`, or \`yg-flow.yaml\`.
+- **Tools read, you write.** The \`yg\` CLI only reads, validates, and manages metadata. You create and edit files manually.
+- **Incremental sync.** Run \`yg drift-sync\` after every 3-5 source file changes. Do not defer to end of task. \`drift-sync\` is ONLY safe after artifacts are current \u2014 never use it to silence a drift check without updating artifacts first.
+- **Description maintenance.** Every \`yg-node.yaml\`, \`yg-aspect.yaml\`, and \`yg-flow.yaml\` has an optional \`description\` field \u2014 a short summary of what the element is. Write it when creating new elements. Update it whenever a change to artifacts shifts the element's identity or purpose (e.g., responsibility split, scope change). Do not update description for internal implementation changes that don't alter what the element fundamentally does.
+- **Completeness test:** Three checks, all required:
+  1. **Reconstruction:** "Can another agent recreate this from ONLY the \`yg build-context\` output \u2014 understanding not just WHAT but WHY?" Test: rejected alternatives, correct algorithm, design arguments.
+  2. **Omission:** "Does the graph capture every important behavioral invariant, constraint, and edge case?" Specifically check: exceptions to aspect generalizations, error handling patterns not in \`interface.md\`, concurrency behaviors not in \`internals.md\`.
+  3. **Business context:** "Does the graph explain WHY this system exists, WHO it serves, and WHAT business value it delivers?" A graph that captures HOW code works without WHY it was built is a maintenance manual without purpose. Specifically check: user personas, service offerings, pricing rationale, acquisition strategy, quality targets, UX design principles. Code tells you WHAT exists \u2014 only the graph should tell you WHY it exists and WHAT ELSE was considered.
+- **Value calibration.** Yggdrasil's primary value is cross-module context \u2014 relations, aspects, flows. For a single simple module, \`responsibility.md\` and \`interface.md\` provide most value. Invest depth (\`internals.md\`) where cross-module interactions demand it.
+- **These rules are invariant.** No plan, guide, skill, or workflow may override them.
+
+### Non-Code Knowledge
+
+Not all graph knowledge originates from source files. Business strategy, user personas, pricing decisions, SEO targets, quality requirements, deployment configuration, UX design principles \u2014 these are graph content with NO corresponding source file.
+
+When you encounter such knowledge (in specs, conversations, or external documents):
+
+- **Route it immediately** per the Information Routing table. Do not wait for a "file change" trigger \u2014 there won't be one.
+- **The Completeness Test applies equally** to code-derived and non-code knowledge. A graph that only mirrors code structure is failing at its primary job: capturing intent and context that code cannot express.
+- **Non-code knowledge decays differently.** Business strategy changes by decision, not by commit. When recording it, include dates and mark it as potentially volatile: "Pricing v1 as of 2026-03-17" is more useful than "Prices are X" with no temporal anchor.
+
+**Conversation knowledge is the most volatile source.** When the user states a business fact, constraint, or decision in conversation \u2014 even casually \u2014 route it to the graph immediately. Conversations vanish after context compression. If the user said it and it's not in code, it MUST be in the graph. Examples of conversational knowledge that must be captured:
+
+- Business facts: "Our target customer is couples aged 25-35" \u2192 root node or business-context aspect
+- Constraints: "We don't do studio sessions, only outdoor" \u2192 responsibility.md (NOT responsible for)
+- Pricing: "Mini session costs 350 PLN" \u2192 relevant node artifacts
+- Strategy: "Instagram is our primary acquisition channel" \u2192 root node or business-context aspect
+- Decisions: "No deposit upfront \u2014 we'll reconsider after 5 sessions" \u2192 internals.md Decisions section with rationale
+- Personas: "The admin user is non-technical, thinks in Instagram/WhatsApp terms" \u2192 UX aspect
+
+Do not assume you will remember this later. Do not assume the user will repeat it. Capture it now or lose it forever.
+
+**Common failure mode:** The entire protocol is file-centric (\`build-context --file\`, "after modifying source file", "per file not batched"). This means knowledge that doesn't map to a specific source file has no natural trigger for capture. Treat spec documents, user conversations, and business decisions as first-class inputs to the graph \u2014 not just context for coding.
+
+### Aspect Discovery During Implementation
+
+Aspects emerge from patterns across features. During greenfield implementation of multiple features:
+
+- **After implementing 3+ features in the same area, pause and review:** Are there repeated patterns (autosave, version history, confirmation modals, empty states)? Are there shared UX rules from a persona doc? Are there quality requirements from specs? Extract them to aspects NOW.
+- **Do NOT wait until all features are done.** Aspect extraction after 3 features captures the pattern while context is fresh. After 30 features, the rationale is forgotten and the aspect becomes a mechanical extraction without WHY.
+- **Watch for "invisible" aspects:** UX patterns (autosave everywhere), quality constraints (WCAG level, Lighthouse targets), and business rules (Polish locale, price-in-grosz) are cross-cutting but don't feel "architectural." They are still aspects.
+- **Trigger:** If you notice yourself implementing the same pattern for the third time, stop coding and create the aspect first. Then continue with the aspect applied to the current and previous nodes.
+
+### CLI Reference
+
+\`\`\`
+yg preflight [--quick]              Unified diagnostic: drift + status + validate.
+yg owner --file <path>              Find the node that owns this file (quick check).
+yg build-context --file <path>      Resolve owner + assemble context in one step.
+yg build-context --node <path>      Assemble context map for a known node.
+yg build-context --node <path> --full  Same map + file contents appended below separator.
+yg tree [--root <path>] [--depth N] Print graph structure.
+yg aspects                          List aspects with metadata (YAML output).
+yg flows                            List flows with metadata (YAML output).
+yg select --task <description> [--limit <n>]
+                                    Find graph nodes relevant to a task description.
+yg deps --node <path> [--depth N] [--type structural|event|all]
+                                    Show dependencies.
+yg impact --file <path>             Resolve owner + show blast radius in one step.
+yg impact --node <path> --simulate  Simulate blast radius (works with --file too).
+yg impact --node <path> --method <name>  Filter to dependents consuming a method (works with --file too).
+yg impact --aspect <id>             Show all nodes where aspect is effective.
+yg impact --flow <name>             Show flow participants and descendants.
+yg status                           Graph health: nodes, coverage, drift summary.
+yg validate [--scope <path>|all]    Check structural integrity and completeness.
+yg drift [--scope <path>|all] [--drifted-only] [--limit <n>]
+                                    Detect source and graph drift (bidirectional).
+yg drift-sync --node <path> [--recursive] | --all
+                                    Record file hashes as new baseline.
+\`\`\`
+
+### Quick Routing Table
+
+| What you have | Where it goes |
+|---|---|
+| Information specific to this node | Local node artifact (check \`yg-config.yaml artifacts\` for types) |
+| Rule that applies to many nodes | Aspect (content \`.md\` files in \`aspects/<id>/\`) |
+| Architectural invariant for a node type | Required aspect in \`yg-config.yaml node_types\` |
+| Business process participation | Flow (\`yg-flow.yaml nodes\`) |
+| Process-level requirement | Flow \`aspects\` + aspect directory |
+| Context shared across a domain | Parent node artifact |
+| Technology stack | Node artifact at appropriate hierarchy level |
+| Coding standards | Node artifact at appropriate hierarchy level |
+| Business strategy (personas, pricing, channels) | Root node artifact or dedicated business-context aspect |
+| Quality targets (perf budgets, a11y, test goals) | Aspect per quality dimension |
+| UX patterns (autosave, version history, empty states) | Aspect when pattern applies to 3+ screens |
+| Infrastructure/deployment (domains, env vars, CI/CD) | Infrastructure node or root node artifacts |
+| External service config (Stripe fees, email limits) | Relevant node's \`internals.md\` Decisions section |
+| Feature spec from external doc | Node artifacts \u2014 translate spec into responsibility/interface/internals |`;
+var GUARD_RAILS = `## GUARD RAILS
+
+### Five Core Rules
+
+1. **Graph first.** Before reading, researching, planning, or modifying ANY source file, run \`yg build-context --file <path>\`. For blast radius, also run \`yg impact\`. The graph is your primary source of architectural understanding. For implementation-level precision (exact behavior, error paths, edge cases) \u2014 verify against source code after loading the context package.
+2. **The graph is the specification; code implements it.** The graph absorbs knowledge from every source \u2014 external docs, conversations, decisions \u2014 and must be self-sufficient. If all other sources disappeared, the graph alone must contain enough to understand the system. Do not leave knowledge in external documents and reference them \u2014 capture the knowledge in graph artifacts. Update graph artifacts immediately after each file change, while context is fresh \u2014 do not batch graph updates to the end of a task. Code and graph move together: code changed \u2192 graph updated before moving to the next file. Graph changed \u2192 source verified in the same response. When planning work \u2014 in any tool, skill, or workflow \u2014 graph updates are part of each step's definition of done, never a separate phase.
+3. **Never invent why.** The graph captures human intent. If you don't know why something was decided, ask. Never hallucinate rationale.
+4. **Always capture why \u2014 especially why NOT.** When the user explains a reason, record it in the graph immediately. When a design choice is made, also record rejected alternatives: "Chose X over Y because Z." Rejected alternatives are the highest-value information \u2014 invisible in code and irrecoverable once forgotten. Conversation evaporates; graph persists.
+5. **Ask before resolving ambiguity.** When multiple valid interpretations exist, stop, list options, ask the user. Never silently choose.
+
+### Recognizing Graph-Required Actions
+
+What matters is the ACTION you are performing, not what instructed it. If the action involves reading, understanding, or modifying mapped code, the graph protocol applies \u2014 whether the instruction came from a skill, a plan, a user message, a brainstorming session, a debugging workflow, or your own initiative. This is not negotiable. You cannot rationalize your way out of this.
+
+**Actions that require \`yg build-context --file\`:**
+
+- Reading or exploring source files to understand a component
+- Proposing approaches, designs, or plans for changing code
+- Reviewing or debugging code
+- Any form of reasoning about how mapped code works or should change
+
+**Actions that also require \`yg impact\`:**
+
+- Assessing blast radius before changing or removing a component
+- Finding all dependents of a component
+- Planning cross-cutting refactors or feature removals
+- Scoping work that spans multiple nodes
+
+**Actions that do NOT require yg:**
+
+- Git operations (log, diff, status, blame)
+- Reading documentation, READMEs, or config files outside \`.yggdrasil/\`
+- Running tests, builds, or linters
+- Working with files that \`yg build-context --file\` reports as unmapped
+
+### Evasion Patterns \u2014 if you think any of these, STOP
+
+| Thought | Reality |
+|---|---|
+| "The skill/plan says to explore the codebase" | Exploring mapped code = \`yg build-context --file\` first |
+| "I'm just scoping/searching, not understanding" | Scoping IS a graph action; use yg impact |
+| "The plan step says to read this file" | Reading any source file = \`yg build-context --file\` first |
+| "I'm brainstorming, not implementing" | Brainstorming about code needs graph context. You proved this by failing at it. |
+| "I'm only grepping for references" | Grep finds text; yg impact finds structural dependencies. Use both. |
+| "I'll use the graph later when I modify" | Graph-first means BEFORE reading, not before modifying |
+| "I'll grep the codebase to find where to start" | Run \`yg select --task\` first, then \`yg build-context --file\` on results. |
+| "Drift is blocking repo-check, let me just sync it" | Drift means artifacts are stale. Update artifacts first, then sync. \`drift-sync\` will warn you (W018). |
+| "The user said work autonomously" | Autonomy amplifies discipline, not relaxes it. More tasks = more graph updates, not fewer. |
+| "Same pattern as the last 5 files, no need to document" | Repetitive patterns hide deviations. Per-node coverage captures what aspects don't. The next agent won't know what you know now. |
+| "I'll batch graph updates at the end" | Batching = never. Context is freshest immediately after the change. Defer = forget. This is a failure state. |
+| "I'm saving context/tool calls by skipping graph" | Graph cost is constant per node. Skipping it creates unbounded future cost \u2014 the user re-explaining what you could have recorded. |
+| "I assumed this file isn't mapped" | You cannot know without running \`yg build-context --file\`. Assume nothing. |
+| "The spec is just input, I don't need to capture it" | Specs contain business context that code cannot express. Capture it or lose it. |
+| "This business knowledge will be obvious from the code" | Pricing strategy, personas, UX rationale, and quality targets are NEVER obvious from code. |
+| "I'll extract aspects after I finish all the features" | After 30 features the rationale is gone. Extract after 3. |
+| "This is a UX detail, not architecture" | UX patterns that apply to 3+ screens ARE cross-cutting requirements. Create an aspect. |
+| "The user just mentioned it casually, it's not a formal decision" | Casual statements ARE decisions. "We don't do studio" is a business constraint. Capture it now or lose it after context compression. |
+| "I'll remember this from the conversation" | No you won't. Context gets compressed. The user won't repeat it. Write it to the graph now. |
+
+### Failure States
+
+You have broken Yggdrasil if you do any of the following:
+
+- \u274C Worked on a source file without running \`yg build-context --file\` first \u2014 regardless of what instructed the action (skill, plan, user request, workflow step).
+- \u274C Modified source code without updating graph artifacts before moving to the next file, or vice versa.
+- \u274C Batched graph updates to "do later" \u2014 deferred = forgotten. Update after EACH file.
+- \u274C Resolved a code-graph inconsistency or ambiguity without asking the user first.
+- \u274C Created or edited a graph element without reading its schema in \`schemas/\` first.
+- \u274C Ran \`yg drift-sync\` before both graph artifacts and source code are current. (CLI will warn you: W018.)
+- \u274C Placed a cross-cutting requirement in a local artifact instead of an aspect, or used an aspect id with no \`aspects/\` directory.
+- \u274C Invented a rationale, business rule, or decision \u2014 or recorded a decision without documenting rejected alternatives and rationale (use "rationale: unknown" if unknown).
+- \u274C Used blackbox coverage for greenfield (new) code.
+- \u274C Deleted or shortened graph artifact content to reduce context package size instead of splitting the node.
+- \u274C Created one wide node for many files instead of granular nodes with focused responsibilities. (CLI will warn you: W017.)
+- \u274C Implemented features from a spec without first transferring spec knowledge (business context, UX rules, quality targets) into the graph. Code without captured intent is a maintenance trap.
+- \u274C Implemented 3+ features sharing a pattern (autosave, version history, empty states) without extracting it to an aspect. Deferred aspect discovery = lost rationale.
+- \u274C Left business strategy, personas, or quality targets only in external documents instead of routing them to graph artifacts. External docs are input; the graph is the persistent store.
+- \u274C Heard the user state a business fact, constraint, or decision in conversation and did not record it in the graph. Conversations are the most volatile knowledge source \u2014 they vanish after context compression and the user will not repeat them.
+
+### Reverse Engineering
+
+**Order:** aspects (cross-cutting patterns) \u2192 flows (business processes) \u2192 model nodes. Never create nodes before aspects and flows are understood.
+
+Per area checklist:
+
+- [ ] 1. \`yg build-context --file <path>\` \u2014 confirm no coverage
+- [ ] 2. Determine node granularity \u2014 propose to user if unclear
+- [ ] 3. Create node directory, read \`schemas/yg-node.yaml\`, create \`yg-node.yaml\`
+- [ ] 3b. Write \`description\` in \`yg-node.yaml\` \u2014 a short summary of what the node does
+- [ ] 4. Analyze source \u2014 for each artifact type in \`yg-config.yaml artifacts\`: extract content, do not invent
+- [ ] 5. Identify relations \u2014 add to \`yg-node.yaml\`
+- [ ] 6. Identify cross-cutting requirements \u2014 add matching aspects, create if needed
+- [ ] 6b. For each aspect on the node: identify 2-5 code anchors (function names, constants) that evidence the pattern \u2192 add as \`anchors\` in the aspect entry in \`yg-node.yaml\`
+- [ ] 7. Identify business process participation \u2014 add to flow, ask user if process unclear
+- [ ] 8. \`yg validate\` \u2014 fix errors
+- [ ] 9. \`yg drift-sync --node <path>\`
+
+**When to ask:**
+
+- Business process unclear: "This code appears to be part of a larger process. Can you describe what it means from a business perspective?"
+- Constraint without rationale: "I see [constraint X]. Do you know why this exists? I want to record the reason, not just the rule."
+- Unexplained architectural choice: "I see [approach X]. What was the reason for this choice?"
+- Decision without alternatives: "You chose [X]. What alternatives did you consider, and why did you reject them?" Record the answer in the Decisions section of \`internals.md\`.
+- Decision without known rationale: Record the decision in \`internals.md\` with "rationale: unknown \u2014 inferred from code, not confirmed by developer." A recorded decision with unknown rationale is infinitely more valuable than no record at all, and safer than an invented rationale.
+
+### Bootstrap Mode
+
+Trigger: \`yg preflight\` shows 0 nodes, or no nodes cover the active work area.
+
+- [ ] 1. Identify the active work area (files the user wants to modify)
+- [ ] 2. Scan for cross-cutting patterns \u2192 create aspects
+- [ ] 3. Ask user about business processes \u2192 create flows if applicable
+- [ ] 4. Propose node structure for the area
+- [ ] 5. Create node(s) with initial artifacts, map files
+- [ ] 6. \`yg validate\`, \`yg drift-sync\`
+- [ ] 7. Proceed with user's original request
+
+Constraint: Do NOT map the entire repository. Focus on the active area. Expand incrementally.
+
+### Drift Resolution
+
+Always ask the user before resolving drift. Never auto-resolve.
+
+- **Source drift** (source files changed) \u2192 update graph artifacts to match source, then \`yg drift-sync\`
+- **Graph drift** (graph artifacts changed) \u2192 review affected source, update if needed, then \`yg drift-sync\`
+- **Full drift** (both changed) \u2192 present both sides to user, ask which direction wins
+- **Missing** \u2192 ask: re-materialize or remove mapping?
+- **Unmaterialized** \u2192 ask user how to proceed
+
+Threshold: >10 drifted nodes \u2192 ask user which area to prioritize. Do not resolve all at once.
+
+**Drift triage:** Prioritize aspects and \`internals.md\` (highest decay rate), then \`responsibility.md\` and \`interface.md\` (most stable).
+
+### Graph Audit
+
+When reviewing graph quality (triggered by user or quality improvement):
+
+**Step 1 \u2014 Consistency** (catches WRONG information):
+
+- [ ] 1. \`yg build-context --node <path>\`
+- [ ] 2. Read mapped source files
+- [ ] 3. For each claim in graph: verify against source code
+- [ ] 4. For each aspect: verify the pattern holds in THIS node. If it deviates, add \`exceptions\` to the aspect entry in \`yg-node.yaml\`
+- [ ] 5. Report inconsistencies
+
+**Step 2 \u2014 Completeness** (catches MISSING information):
 
-- \`schema\` \u2014 enforced by data model; review only when data model changes (most stable)
-- \`protocol\` \u2014 contractual pattern; review when contracts or interfaces change
-- \`implementation\` \u2014 specific mechanism; review after ANY significant code change (least stable)
+- [ ] 1. For each public method: is it in \`interface.md\`?
+- [ ] 2. For each error path: is it in \`interface.md\` (Failure Modes section)?
+- [ ] 3. For each behavioral invariant: is it in the graph?
+- [ ] 4. Report omissions separately from inconsistencies
 
-When code anchors (\`anchors\` in an aspect entry in \`yg-node.yaml\`) are present, they list code patterns (function names, constants, SQL fragments) evidencing the aspect's implementation in this node. \`yg validate\` checks that each anchor exists in the node's mapped source files \u2014 a missing anchor (W014) signals the aspect may be stale for this node.
+**Step 3 \u2014 Non-Derivable Knowledge** (catches knowledge that exists ONLY in external docs or conversations, not in code):
 
-### Creating Flows
+- [ ] 1. For each business rule embedded in code: is the WHY recorded in the graph, or only the WHAT visible in code?
+- [ ] 2. For each design decision: is the rationale AND rejected alternatives recorded?
+- [ ] 3. For each external constraint (brand guidelines, legal, UX persona, quality targets): is it in the graph?
+- [ ] 4. For each cross-cutting pattern implemented in 3+ places: does an aspect exist?
+- [ ] 5. Report non-derivable knowledge gaps separately \u2014 these are the highest-value omissions because they cannot be recovered by reading code.
 
-- [ ] 1. Read \`schemas/yg-flow.yaml\`
-- [ ] 2. Create \`flows/<name>/\` directory
-- [ ] 3. Write \`yg-flow.yaml\` \u2014 name, description, nodes (participant list), and flow-level aspects
-- [ ] 4. Write \`description.md\` with required sections: Business context, Trigger, Goal, Participants, Paths (at least Happy path), Invariants across all paths
-- [ ] 5. \`yg validate\`
+### Error Recovery
 
-Test: "Does this describe what happens in the world, or only in the software?" If only software \u2014 rewrite.
+- **\`yg\` not found** \u2192 inform user: "yg CLI is not installed or not in PATH." Stop.
+- **Unfixable validate errors** \u2192 if not resolved after 3 attempts, stop and report to user. Do not loop.
+- **Budget warning (W005/W006)** \u2192 informational. \`yg validate\` shows a breakdown (own/hierarchy/aspects/flows/dependencies). Large inherited context means the system is complex \u2014 this is not a problem to fix, it is reality to acknowledge. Do not delete knowledge from artifacts. Do not attempt to "reduce" inherited context.
+- **Own budget warning (W015)** \u2192 own artifacts are large. Consider splitting this node's responsibilities into child nodes. Redistribute knowledge across children so total knowledge is preserved or increased, never reduced.
+- **Corrupted \`.yggdrasil/\` files** \u2192 report to user. Do not attempt repair.
+- **Incremental sync** \u2192 run \`yg drift-sync\` every 3-5 source files during multi-file tasks. Do not defer to end. But NEVER run \`yg drift-sync\` to silence a failing drift check \u2014 drift is a signal that artifacts need updating. First update artifacts, then sync.
 
-**Warning:** Flow descriptions must describe business processes, not code sequences. "The OrderService calls PaymentGateway.charge()" is WRONG. "The system charges the customer's payment method" is CORRECT.
+### Escape Hatch
 
-### Operational Rules
+If the user explicitly requests a code-only change, comply but:
 
-- **English only** for all files in \`.yggdrasil/\`. Conversation can be any language.
-- **Read schemas before creating** any \`yg-node.yaml\`, \`yg-aspect.yaml\`, or \`yg-flow.yaml\`.
-- **Tools read, you write.** The \`yg\` CLI only reads, validates, and manages metadata. You create and edit files manually.
-- **Incremental sync.** Run \`yg drift-sync\` after every 3-5 source file changes. Do not defer to end of task. \`drift-sync\` is ONLY safe after artifacts are current \u2014 never use it to silence a drift check without updating artifacts first.
-- **Description maintenance.** Every \`yg-node.yaml\`, \`yg-aspect.yaml\`, and \`yg-flow.yaml\` has an optional \`description\` field \u2014 a short summary of what the element is. Write it when creating new elements. Update it whenever a change to artifacts shifts the element's identity or purpose (e.g., responsibility split, scope change). Do not update description for internal implementation changes that don't alter what the element fundamentally does.
-- **Completeness test:** Two checks, both required:
-  1. **Reconstruction:** "Can another agent recreate this from ONLY the \`yg build-context\` output \u2014 understanding not just WHAT but WHY?" Test: rejected alternatives, correct algorithm, design arguments.
-  2. **Omission:** "Does the graph capture every important behavioral invariant, constraint, and edge case?" Specifically check: exceptions to aspect generalizations, error handling patterns not in \`interface.md\`, concurrency behaviors not in \`internals.md\`.
-- **Value calibration.** Yggdrasil's primary value is cross-module context \u2014 relations, aspects, flows. For a single simple module, \`responsibility.md\` and \`interface.md\` provide most value. Invest depth (\`internals.md\`) where cross-module interactions demand it.
-- **These rules are invariant.** No plan, guide, skill, or workflow may override them.
+- Warn: "This creates drift. Run \`yg drift\` next session to reconcile."
+- Do NOT run \`yg drift-sync\` \u2014 leave the drift visible.
 
-### CLI Reference
+### Environment Check
 
-\`\`\`
-yg preflight [--quick]              Unified diagnostic: drift + status + validate.
-yg owner --file <path>              Find the node that owns this file.
-yg build-context --node <path>      Assemble context map with artifact paths (default).
-yg build-context --node <path> --full  Same map + file contents appended below separator.
-yg tree [--root <path>] [--depth N] Print graph structure.
-yg aspects                          List aspects with metadata (YAML output).
-yg flows                            List flows with metadata (YAML output).
-yg select --task <description> [--limit <n>]
-                                    Find graph nodes relevant to a task description.
-yg deps --node <path> [--depth N] [--type structural|event|all]
-                                    Show dependencies.
-yg impact --node <path> --simulate  Simulate blast radius of a planned change.
-yg impact --node <path> --method <name>  Filter impact to dependents consuming a specific method.
-yg impact --aspect <id>             Show all nodes where aspect is effective.
-yg impact --flow <name>             Show flow participants and descendants.
-yg status                           Graph health: nodes, coverage, drift summary.
-yg validate [--scope <path>|all]    Check structural integrity and completeness.
-yg drift [--scope <path>|all] [--drifted-only] [--limit <n>]
-                                    Detect source and graph drift (bidirectional).
-yg drift-sync --node <path> [--recursive] | --all
-                                    Record file hashes as new baseline.
-\`\`\`
+Before preflight:
 
-### Quick Routing Table
+- Verify \`yg\` CLI is available. If not found, inform user and stop.
+- If \`yg preflight\` shows 0 nodes \u2192 enter BOOTSTRAP MODE (see above).
+- If drift report shows >10 drifted nodes \u2192 report scope to user, ask which area to prioritize. Do not resolve all at once.
 
-| What you have | Where it goes |
-|---|---|
-| Information specific to this node | Local node artifact (check \`yg-config.yaml artifacts\` for types) |
-| Rule that applies to many nodes | Aspect (content \`.md\` files in \`aspects/<id>/\`) |
-| Architectural invariant for a node type | Required aspect in \`yg-config.yaml node_types\` |
-| Business process participation | Flow (\`yg-flow.yaml nodes\`) |
-| Process-level requirement | Flow \`aspects\` + aspect directory |
-| Context shared across a domain | Parent node artifact |
-| Technology stack | Node artifact at appropriate hierarchy level |
-| Coding standards | Node artifact at appropriate hierarchy level |`;
-var AGENT_RULES_CONTENT = [CORE_PROTOCOL, OPERATIONS, KNOWLEDGE_BASE].join("\n\n---\n\n") + "\n";
+<critical_protocol>
+BEFORE reading, analyzing, or modifying ANY source file:
+  \`yg build-context --file <path>\`
+One command. No exceptions. No "I'll do it later." No "this is just analysis."
+</critical_protocol>`;
+var AGENT_RULES_CONTENT = [PROTOCOL, REFERENCE, GUARD_RAILS].join("\n\n---\n\n") + "\n";
 
 // src/templates/platform.ts
 var AGENT_RULES_IMPORT = "@.yggdrasil/agent-rules.md";
@@ -2376,6 +2515,7 @@ async function validate(graph, scope = "all") {
   issues.push(...checkFlowAspectIds(graph));
   issues.push(...await checkDirectoriesHaveNodeYaml(graph));
   issues.push(...await checkShallowArtifacts(graph));
+  issues.push(...await checkWideNodes(graph));
   issues.push(...checkUnpairedEvents(graph));
   let filtered = issues;
   let nodesScanned = graph.nodes.size;
@@ -2857,6 +2997,29 @@ async function checkShallowArtifacts(graph) {
   }
   return issues;
 }
+async function checkWideNodes(graph) {
+  const issues = [];
+  const maxFiles = graph.config.quality?.max_mapping_source_files ?? 10;
+  const projectRoot = path11.dirname(graph.rootPath);
+  for (const [nodePath, node] of graph.nodes) {
+    if (node.meta.blackbox) continue;
+    const mappingPaths = normalizeMappingPaths(node.meta.mapping);
+    if (mappingPaths.length === 0) continue;
+    const sourceFiles = await expandMappingToFiles(projectRoot, mappingPaths);
+    if (sourceFiles.length <= maxFiles) continue;
+    const filledArtifacts = node.artifacts.filter(
+      (a) => a.content.trim().length >= (graph.config.quality?.min_artifact_length ?? 50)
+    ).length;
+    issues.push({
+      severity: "warning",
+      code: "W017",
+      rule: "wide-node",
+      message: `Node maps ${sourceFiles.length} source files (max: ${maxFiles}) with ${filledArtifacts} artifact(s). Consider splitting into child nodes with focused responsibilities.`,
+      nodePath
+    });
+  }
+  return issues;
+}
 function checkHighFanOut(graph) {
   const issues = [];
   const maxRel = graph.config.quality?.max_direct_relations ?? 10;
@@ -3134,6 +3297,73 @@ function checkMissingDescriptions(graph) {
   return issues;
 }
 
+// src/cli/owner.ts
+import path12 from "path";
+import { access as access2 } from "fs/promises";
+function normalizeForMatch(inputPath) {
+  return inputPath.replace(/\\/g, "/").replace(/\/+$/, "");
+}
+function findOwner(graph, projectRoot, rawPath) {
+  const file = normalizeForMatch(normalizeProjectRelativePath(projectRoot, rawPath));
+  let best = null;
+  for (const [nodePath, node] of graph.nodes) {
+    const mappingPaths = normalizeMappingPaths(node.meta.mapping).map(normalizeForMatch).filter((mappingPath) => mappingPath.length > 0);
+    for (const mappingPath of mappingPaths) {
+      if (file === mappingPath) {
+        return { file, nodePath, mappingPath, direct: true };
+      }
+      if (file.startsWith(mappingPath + "/")) {
+        if (!best || best && mappingPath.length > best.mappingPath.length) {
+          best = { nodePath, mappingPath, exact: false };
+        }
+      }
+    }
+  }
+  return best ? { file, nodePath: best.nodePath, mappingPath: best.mappingPath, direct: false } : { file, nodePath: null };
+}
+function registerOwnerCommand(program2) {
+  program2.command("owner").description("Find which graph node owns a source file").requiredOption("--file <path>", "File path (relative to repository root)").action(async (options) => {
+    try {
+      const cwd = process.cwd();
+      const graph = await loadGraph(cwd);
+      const repoRoot = projectRootFromGraph(graph.rootPath);
+      const rawPath = options.file.trim();
+      const absolute = path12.resolve(cwd, rawPath);
+      const repoRelative = path12.relative(repoRoot, absolute).split(path12.sep).join("/");
+      const result = findOwner(graph, repoRoot, repoRelative);
+      if (!result.nodePath) {
+        const absPath = path12.resolve(repoRoot, result.file);
+        let exists = true;
+        try {
+          await access2(absPath);
+        } catch {
+          exists = false;
+        }
+        if (exists) {
+          process.stdout.write(`${result.file} -> no graph coverage
+`);
+        } else {
+          process.stdout.write(`${result.file} -> no graph coverage (file not found)
+`);
+        }
+      } else {
+        process.stdout.write(`${result.file} -> ${result.nodePath}
+`);
+        if (result.direct === false && result.mappingPath) {
+          process.stdout.write(
+            `  File has no direct mapping; context comes from ancestor directory ${result.mappingPath}. Use: yg build-context --node ${result.nodePath}
+`
+          );
+        }
+      }
+    } catch (error) {
+      process.stderr.write(`Error: ${error.message}
+`);
+      process.exit(1);
+    }
+  });
+}
+
 // src/cli/build-context.ts
 function collectRelevantNodePaths(graph, nodePath) {
   const relevant = /* @__PURE__ */ new Set();
@@ -3155,10 +3385,32 @@ function collectRelevantNodePaths(graph, nodePath) {
   return relevant;
 }
 function registerBuildCommand(program2) {
-  program2.command("build-context").description("Assemble a context package for one node").requiredOption("--node <node-path>", "Node path relative to .yggdrasil/model/").option("--full", "Include artifact file contents in output").action(async (options) => {
+  program2.command("build-context").description("Assemble a context package for one node").option("--node <node-path>", "Node path relative to .yggdrasil/model/").option("--file <file-path>", "Source file path \u2014 resolves owner node automatically").option("--full", "Include artifact file contents in output").action(async (options) => {
     try {
+      if (!options.node && !options.file) {
+        process.stderr.write("Error: either '--node <path>' or '--file <path>' is required\n");
+        process.exit(1);
+      }
+      if (options.node && options.file) {
+        process.stderr.write("Error: '--node' and '--file' are mutually exclusive\n");
+        process.exit(1);
+      }
       const graph = await loadGraph(process.cwd());
-      const nodePath = options.node.trim().replace(/^\.\//, "").replace(/\/$/, "");
+      let nodePath;
+      if (options.file) {
+        const repoRoot = projectRootFromGraph(graph.rootPath);
+        const result = findOwner(graph, repoRoot, options.file.trim());
+        if (!result.nodePath) {
+          process.stderr.write(`${result.file} -> no graph coverage
+`);
+          process.exit(1);
+        }
+        process.stderr.write(`${result.file} -> ${result.nodePath}
+`);
+        nodePath = result.nodePath;
+      } else {
+        nodePath = options.node.trim().replace(/^\.\//, "").replace(/\/$/, "");
+      }
       const relevantNodes = collectRelevantNodePaths(graph, nodePath);
       const validationResult = await validate(graph, "all");
       const relevantErrors = validationResult.issues.filter(
@@ -3305,11 +3557,11 @@ import chalk2 from "chalk";
 
 // src/io/drift-state-store.ts
 import { readFile as readFile14, writeFile as writeFile5, stat as stat5, readdir as readdir6, mkdir as mkdir3, rm as rm2 } from "fs/promises";
-import path12 from "path";
+import path13 from "path";
 import { parse as yamlParse } from "yaml";
 var DRIFT_STATE_DIR = ".drift-state";
 function nodeStatePath(yggRoot, nodePath) {
-  return path12.join(yggRoot, DRIFT_STATE_DIR, `${nodePath}.json`);
+  return path13.join(yggRoot, DRIFT_STATE_DIR, `${nodePath}.json`);
 }
 async function scanJsonFiles(dir, baseDir) {
   const results = [];
@@ -3320,12 +3572,12 @@ async function scanJsonFiles(dir, baseDir) {
     return results;
   }
   for (const entry of entries) {
-    const fullPath = path12.join(dir, entry.name);
+    const fullPath = path13.join(dir, entry.name);
     if (entry.isDirectory()) {
       const nested = await scanJsonFiles(fullPath, baseDir);
       results.push(...nested);
     } else if (entry.isFile() && entry.name.endsWith(".json")) {
-      const relPath = path12.relative(baseDir, fullPath);
+      const relPath = path13.relative(baseDir, fullPath);
       const nodePath = relPath.replace(/\\/g, "/").replace(/\.json$/, "");
       results.push(nodePath);
     }
@@ -3333,13 +3585,13 @@ async function scanJsonFiles(dir, baseDir) {
   return results;
 }
 async function removeEmptyParents(filePath, stopDir) {
-  let dir = path12.dirname(filePath);
+  let dir = path13.dirname(filePath);
   while (dir !== stopDir && dir.startsWith(stopDir)) {
     try {
       const entries = await readdir6(dir);
       if (entries.length === 0) {
         await rm2(dir, { recursive: true });
-        dir = path12.dirname(dir);
+        dir = path13.dirname(dir);
       } else {
         break;
       }
@@ -3360,12 +3612,12 @@ async function readNodeDriftState(yggRoot, nodePath) {
 }
 async function writeNodeDriftState(yggRoot, nodePath, nodeState) {
   const filePath = nodeStatePath(yggRoot, nodePath);
-  await mkdir3(path12.dirname(filePath), { recursive: true });
+  await mkdir3(path13.dirname(filePath), { recursive: true });
   const content = JSON.stringify(nodeState, null, 2) + "\n";
   await writeFile5(filePath, content, "utf-8");
 }
 async function garbageCollectDriftState(yggRoot, validNodePaths) {
-  const driftDir = path12.join(yggRoot, DRIFT_STATE_DIR);
+  const driftDir = path13.join(yggRoot, DRIFT_STATE_DIR);
   const allNodePaths = await scanJsonFiles(driftDir, driftDir);
   const removed = [];
   for (const nodePath of allNodePaths) {
@@ -3379,7 +3631,7 @@ async function garbageCollectDriftState(yggRoot, validNodePaths) {
   return removed.sort();
 }
 async function readDriftState(yggRoot) {
-  const driftPath = path12.join(yggRoot, DRIFT_STATE_DIR);
+  const driftPath = path13.join(yggRoot, DRIFT_STATE_DIR);
   let driftStat;
   try {
     driftStat = await stat5(driftPath);
@@ -3420,7 +3672,7 @@ async function readDriftState(yggRoot) {
 
 // src/utils/hash.ts
 import { readFile as readFile15, readdir as readdir7, stat as stat6 } from "fs/promises";
-import path13 from "path";
+import path14 from "path";
 import { createHash } from "crypto";
 import { createRequire } from "module";
 var require2 = createRequire(import.meta.url);
@@ -3432,7 +3684,7 @@ async function hashFile(filePath) {
 async function loadRootGitignoreStack(projectRoot) {
   if (!projectRoot) return [];
   try {
-    const content = await readFile15(path13.join(projectRoot, ".gitignore"), "utf-8");
+    const content = await readFile15(path14.join(projectRoot, ".gitignore"), "utf-8");
     const matcher = ignoreFactory();
     matcher.add(content);
     return [{ basePath: projectRoot, matcher }];
@@ -3442,7 +3694,7 @@ async function loadRootGitignoreStack(projectRoot) {
 }
 function isIgnoredByStack(candidatePath, stack) {
   for (const { basePath, matcher } of stack) {
-    const relativePath = path13.relative(basePath, candidatePath);
+    const relativePath = path14.relative(basePath, candidatePath);
     if (relativePath === "" || relativePath.startsWith("..")) continue;
     if (matcher.ignores(relativePath) || matcher.ignores(relativePath + "/")) return true;
   }
@@ -3457,7 +3709,7 @@ async function hashTrackedFiles(projectRoot, trackedFiles, storedFileData, exclu
   const gitignoreStack = await loadRootGitignoreStack(projectRoot);
   const allFiles = [];
   for (const tf of trackedFiles) {
-    const absPath = path13.join(projectRoot, tf.path);
+    const absPath = path14.join(projectRoot, tf.path);
     try {
       const st = await stat6(absPath);
       if (st.isDirectory()) {
@@ -3467,7 +3719,7 @@ async function hashTrackedFiles(projectRoot, trackedFiles, storedFileData, exclu
         });
         for (const entry of dirEntries) {
           allFiles.push({
-            relPath: path13.join(tf.path, entry.relPath).replace(/\\/g, "/"),
+            relPath: path14.join(tf.path, entry.relPath).replace(/\\/g, "/"),
             absPath: entry.absPath,
             mtimeMs: entry.mtimeMs
           });
@@ -3507,7 +3759,7 @@ async function hashTrackedFiles(projectRoot, trackedFiles, storedFileData, exclu
 async function collectDirectoryFilePaths(directoryPath, rootDirectoryPath, options) {
   let stack = options.gitignoreStack ?? [];
   try {
-    const localContent = await readFile15(path13.join(directoryPath, ".gitignore"), "utf-8");
+    const localContent = await readFile15(path14.join(directoryPath, ".gitignore"), "utf-8");
     const localMatcher = ignoreFactory();
     localMatcher.add(localContent);
     stack = [...stack, { basePath: directoryPath, matcher: localMatcher }];
@@ -3517,7 +3769,7 @@ async function collectDirectoryFilePaths(directoryPath, rootDirectoryPath, optio
   const dirs = [];
   const files = [];
   for (const entry of entries) {
-    const absoluteChildPath = path13.join(directoryPath, entry.name);
+    const absoluteChildPath = path14.join(directoryPath, entry.name);
     if (isIgnoredByStack(absoluteChildPath, stack)) continue;
     if (entry.isDirectory()) dirs.push(absoluteChildPath);
     else if (entry.isFile()) files.push(absoluteChildPath);
@@ -3530,7 +3782,7 @@ async function collectDirectoryFilePaths(directoryPath, rootDirectoryPath, optio
     Promise.all(files.map(async (f) => {
       const fileStat = await stat6(f);
       return {
-        relPath: path13.relative(rootDirectoryPath, f),
+        relPath: path14.relative(rootDirectoryPath, f),
         absPath: f,
         mtimeMs: fileStat.mtimeMs
       };
@@ -3543,14 +3795,14 @@ async function collectDirectoryFilePaths(directoryPath, rootDirectoryPath, optio
 }
 
 // src/core/context-files.ts
-import path14 from "path";
+import path15 from "path";
 var STRUCTURAL_RELATION_TYPES2 = /* @__PURE__ */ new Set(["uses", "calls", "extends", "implements"]);
 function collectTrackedFiles(node, graph) {
   const seen = /* @__PURE__ */ new Set();
   const result = [];
-  const projectRoot = path14.dirname(graph.rootPath);
-  const yggPrefix = path14.relative(projectRoot, graph.rootPath);
-  const yggPrefixNormalized = yggPrefix.split(path14.sep).join("/");
+  const projectRoot = path15.dirname(graph.rootPath);
+  const yggPrefix = path15.relative(projectRoot, graph.rootPath);
+  const yggPrefixNormalized = yggPrefix.split(path15.sep).join("/");
   const configArtifactKeys = new Set(Object.keys(graph.config.artifacts ?? {}));
   function addFile(filePath, category) {
     if (seen.has(filePath)) return;
@@ -3662,8 +3914,8 @@ function collectParticipatingFlows2(graph, node, ancestors) {
 }
 
 // src/core/drift-detector.ts
-import { access as access2 } from "fs/promises";
-import path15 from "path";
+import { access as access3 } from "fs/promises";
+import path16 from "path";
 function getChildMappingExclusions(graph, nodePath) {
   const node = graph.nodes.get(nodePath);
   if (!node) return [];
@@ -3685,7 +3937,7 @@ function getChildMappingExclusions(graph, nodePath) {
   return exclusions;
 }
 async function detectDrift(graph, filterNodePath) {
-  const projectRoot = path15.dirname(graph.rootPath);
+  const projectRoot = path16.dirname(graph.rootPath);
   const driftState = await readDriftState(graph.rootPath);
   const entries = [];
   for (const [nodePath, node] of graph.nodes) {
@@ -3767,16 +4019,16 @@ async function detectDrift(graph, filterNodePath) {
   };
 }
 function categorizeFile(filePath, _rootPath, projectRoot) {
-  const yggPrefix = path15.relative(projectRoot, _rootPath);
-  const normalizedPrefix = yggPrefix.split(path15.sep).join("/");
+  const yggPrefix = path16.relative(projectRoot, _rootPath);
+  const normalizedPrefix = yggPrefix.split(path16.sep).join("/");
   const normalizedFilePath = filePath.replace(/\\/g, "/");
   return normalizedFilePath.startsWith(normalizedPrefix) ? "graph" : "source";
 }
 async function allPathsMissing(projectRoot, mappingPaths) {
   for (const mp of mappingPaths) {
-    const absPath = path15.join(projectRoot, mp);
+    const absPath = path16.join(projectRoot, mp);
     try {
-      await access2(absPath);
+      await access3(absPath);
       return false;
     } catch {
     }
@@ -3784,7 +4036,7 @@ async function allPathsMissing(projectRoot, mappingPaths) {
   return true;
 }
 async function syncDriftState(graph, nodePath) {
-  const projectRoot = path15.dirname(graph.rootPath);
+  const projectRoot = path16.dirname(graph.rootPath);
   const node = graph.nodes.get(nodePath);
   if (!node) throw new Error(`Node not found: ${nodePath}`);
   if (!node.meta.mapping) throw new Error(`Node has no mapping: ${nodePath}`);
@@ -3794,12 +4046,39 @@ async function syncDriftState(graph, nodePath) {
   const storedFileData = existingEntry?.files ? { hashes: existingEntry.files, mtimes: existingEntry.mtimes ?? {} } : void 0;
   const { canonicalHash, fileHashes, fileMtimes } = await hashTrackedFiles(projectRoot, trackedFiles, storedFileData, excludePrefixes);
   const previousHash = existingEntry?.hash;
+  let sourceOnlyChange = false;
+  if (previousHash && previousHash !== canonicalHash && existingEntry?.files) {
+    let hasSourceChange = false;
+    let hasGraphChange = false;
+    const yggPrefix = path16.relative(projectRoot, graph.rootPath).split(path16.sep).join("/");
+    for (const [filePath, hash] of Object.entries(fileHashes)) {
+      const storedHash = existingEntry.files[filePath];
+      if (storedHash && storedHash === hash) continue;
+      if (!storedHash || storedHash !== hash) {
+        if (filePath.startsWith(yggPrefix)) {
+          hasGraphChange = true;
+        } else {
+          hasSourceChange = true;
+        }
+      }
+    }
+    for (const storedPath of Object.keys(existingEntry.files)) {
+      if (!(storedPath in fileHashes)) {
+        if (storedPath.startsWith(yggPrefix)) {
+          hasGraphChange = true;
+        } else {
+          hasSourceChange = true;
+        }
+      }
+    }
+    sourceOnlyChange = hasSourceChange && !hasGraphChange;
+  }
   await writeNodeDriftState(graph.rootPath, nodePath, {
     hash: canonicalHash,
     files: fileHashes,
     mtimes: fileMtimes
   });
-  return { previousHash, currentHash: canonicalHash };
+  return { previousHash, currentHash: canonicalHash, sourceOnlyChange };
 }
 
 // src/cli/drift.ts
@@ -3972,13 +4251,20 @@ function registerDriftSyncCommand(program2) {
           }
           continue;
         }
-        const { previousHash, currentHash } = await syncDriftState(graph, np);
+        const { previousHash, currentHash, sourceOnlyChange } = await syncDriftState(graph, np);
         process.stdout.write(chalk3.green(`Synchronized: ${np}
 `));
         process.stdout.write(
           `  Hash: ${previousHash ? previousHash.slice(0, 8) : "none"} -> ${currentHash.slice(0, 8)}
 `
         );
+        if (sourceOnlyChange) {
+          process.stderr.write(
+            chalk3.yellow(`  \u26A0 W018: Source files changed but graph artifacts are unchanged for '${np}'.
+`) + chalk3.yellow(`    Update artifacts BEFORE syncing \u2014 drift-sync without artifact update hides staleness.
+`)
+          );
+        }
       }
       if (options.all) {
         const validPaths = new Set(nodesToSync);
@@ -4150,73 +4436,6 @@ function printNode(node, prefix, isLast, depth, maxDepth) {
   }
 }
 
-// src/cli/owner.ts
-import path16 from "path";
-import { access as access3 } from "fs/promises";
-function normalizeForMatch(inputPath) {
-  return inputPath.replace(/\\/g, "/").replace(/\/+$/, "");
-}
-function findOwner(graph, projectRoot, rawPath) {
-  const file = normalizeForMatch(normalizeProjectRelativePath(projectRoot, rawPath));
-  let best = null;
-  for (const [nodePath, node] of graph.nodes) {
-    const mappingPaths = normalizeMappingPaths(node.meta.mapping).map(normalizeForMatch).filter((mappingPath) => mappingPath.length > 0);
-    for (const mappingPath of mappingPaths) {
-      if (file === mappingPath) {
-        return { file, nodePath, mappingPath, direct: true };
-      }
-      if (file.startsWith(mappingPath + "/")) {
-        if (!best || best && mappingPath.length > best.mappingPath.length) {
-          best = { nodePath, mappingPath, exact: false };
-        }
-      }
-    }
-  }
-  return best ? { file, nodePath: best.nodePath, mappingPath: best.mappingPath, direct: false } : { file, nodePath: null };
-}
-function registerOwnerCommand(program2) {
-  program2.command("owner").description("Find which graph node owns a source file").requiredOption("--file <path>", "File path (relative to repository root)").action(async (options) => {
-    try {
-      const cwd = process.cwd();
-      const graph = await loadGraph(cwd);
-      const repoRoot = projectRootFromGraph(graph.rootPath);
-      const rawPath = options.file.trim();
-      const absolute = path16.resolve(cwd, rawPath);
-      const repoRelative = path16.relative(repoRoot, absolute).split(path16.sep).join("/");
-      const result = findOwner(graph, repoRoot, repoRelative);
-      if (!result.nodePath) {
-        const absPath = path16.resolve(repoRoot, result.file);
-        let exists = true;
-        try {
-          await access3(absPath);
-        } catch {
-          exists = false;
-        }
-        if (exists) {
-          process.stdout.write(`${result.file} -> no graph coverage
-`);
-        } else {
-          process.stdout.write(`${result.file} -> no graph coverage (file not found)
-`);
-        }
-      } else {
-        process.stdout.write(`${result.file} -> ${result.nodePath}
-`);
-        if (result.direct === false && result.mappingPath) {
-          process.stdout.write(
-            `  File has no direct mapping; context comes from ancestor directory ${result.mappingPath}. Use: yg build-context --node ${result.nodePath}
-`
-          );
-        }
-      }
-    } catch (error) {
-      process.stderr.write(`Error: ${error.message}
-`);
-      process.exit(1);
-    }
-  });
-}
-
 // src/core/dependency-resolver.ts
 import { execSync } from "child_process";
 import path17 from "path";
@@ -4633,23 +4852,39 @@ Total scope: ${sorted.length + indirectPaths.length} nodes
   }
 }
 function registerImpactCommand(program2) {
-  program2.command("impact").description("Show reverse dependency impact for a node, aspect, or flow").option("--node <path>", "Node path relative to .yggdrasil/model/").option("--aspect <id>", "Aspect id (directory path under aspects/)").option("--flow <name>", "Flow name (directory name under flows/)").option("--method <name>", "Filter impact to dependents consuming a specific method (requires --node)").option("--simulate", "Simulate context package impact (compare HEAD vs current)").action(
+  program2.command("impact").description("Show reverse dependency impact for a node, aspect, or flow").option("--node <path>", "Node path relative to .yggdrasil/model/").option("--file <file-path>", "Source file path \u2014 resolves owner node automatically").option("--aspect <id>", "Aspect id (directory path under aspects/)").option("--flow <name>", "Flow name (directory name under flows/)").option("--method <name>", "Filter impact to dependents consuming a specific method (requires --node or --file)").option("--simulate", "Simulate context package impact (compare HEAD vs current)").action(
     async (options) => {
       try {
-        const modeCount = [options.node, options.aspect, options.flow].filter(Boolean).length;
+        if (options.node && options.file) {
+          process.stderr.write("Error: '--node' and '--file' are mutually exclusive\n");
+          process.exit(1);
+        }
+        const modeCount = [options.node || options.file, options.aspect, options.flow].filter(Boolean).length;
         if (modeCount === 0) {
           process.stderr.write(
-            "Error: one of --node, --aspect, or --flow is required\n"
+            "Error: one of --node, --file, --aspect, or --flow is required\n"
           );
           process.exit(1);
         }
         if (modeCount > 1) {
           process.stderr.write(
-            "Error: --node, --aspect, and --flow are mutually exclusive\n"
+            "Error: --node/--file, --aspect, and --flow are mutually exclusive\n"
           );
           process.exit(1);
         }
         const graph = await loadGraph(process.cwd());
+        if (options.file) {
+          const repoRoot = projectRootFromGraph(graph.rootPath);
+          const result = findOwner(graph, repoRoot, options.file.trim());
+          if (!result.nodePath) {
+            process.stderr.write(`${result.file} -> no graph coverage
+`);
+            process.exit(1);
+          }
+          process.stderr.write(`${result.file} -> ${result.nodePath}
+`);
+          options.node = result.nodePath;
+        }
         if (options.aspect) {
           await handleAspectImpact(graph, options.aspect.trim(), options.simulate);
           return;