mover-os 4.0.11 → 4.0.13

package/install.js

@@ -941,8 +941,34 @@ function installHooksForClaude(bundleDir, vaultPath) {
     count++;
   }
 
+  // Deep-merge hooks into existing settings.json (preserve user config)
   const settingsPath = path.join(settingsDir, "settings.json");
-  if (!fs.existsSync(settingsPath)) {
+  const newHooks = JSON.parse(generateClaudeSettings()).hooks;
+  if (fs.existsSync(settingsPath)) {
+    try {
+      const existing = JSON.parse(fs.readFileSync(settingsPath, "utf8"));
+      if (!existing.hooks) existing.hooks = {};
+      // Merge each hook event (Stop, PreToolUse, PreCompact)
+      for (const [event, entries] of Object.entries(newHooks)) {
+        if (!existing.hooks[event]) {
+          existing.hooks[event] = entries;
+        } else {
+          // Check if our hooks are already registered (by command substring)
+          const existingCmds = JSON.stringify(existing.hooks[event]);
+          const alreadyHas = entries[0].hooks.every(
+            (h) => existingCmds.includes(h.command.split("/").pop().replace('"', ""))
+          );
+          if (!alreadyHas) {
+            existing.hooks[event].push(...entries);
+          }
+        }
+      }
+      fs.writeFileSync(settingsPath, JSON.stringify(existing, null, 2), "utf8");
+    } catch {
+      // Corrupt settings — overwrite
+      fs.writeFileSync(settingsPath, generateClaudeSettings(), "utf8");
+    }
+  } else {
     fs.writeFileSync(settingsPath, generateClaudeSettings(), "utf8");
   }
 
@@ -1046,7 +1072,7 @@ function installCodexCli(bundleDir, vaultPath, skillOpts) {
 function installCodexCloud(bundleDir, vaultPath, skillOpts) {
   const steps = [];
 
-  if (vaultPath && installSkills) {
+  if (vaultPath && skillOpts && skillOpts.install) {
     const skillsDir = path.join(vaultPath, ".agents", "skills");
     const skCount = installSkillPacks(bundleDir, skillsDir, skillOpts.categories);
     if (skCount > 0) steps.push(`${skCount} skills`);
@@ -1471,7 +1497,7 @@ async function main() {
     });
 
     installSkills = selectedCatIds.length > 0;
-    if (skillOpts && skillOpts.install) {
+    if (installSkills) {
       selectedCategories = new Set(selectedCatIds);
       // Count how many skills will be installed (selected categories + tools)
       const skillCount = allSkills.filter((s) => s.category === "tools" || selectedCategories.has(s.category)).length;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mover-os",
-  "version": "4.0.11",
+  "version": "4.0.13",
   "description": "The self-improving OS for AI agents. Turns Obsidian into an execution engine.",
   "bin": {
     "mover-os": "install.js"

package/src/structure/02_Areas/Engine/Active_Context.md

@@ -56,7 +56,27 @@
 
 ---
 
-## 5. ACTIVE SESSIONS (Rolling Buffer)
+## 5. IDENTITY SNAPSHOT
+
+*Written by: `/analyse-day`, `/review-week`, `/setup`. Condensed from Identity_Prime.md. Light workflows read this instead of the full file.*
+
+- **Archetype:** [From Identity_Prime — e.g., "Builder-Strategist"]
+- **Core Drive:** [One sentence — what fuels you]
+- **The Code:** [Top 3 non-negotiable rules from Identity_Prime]
+- **Anti-Identity:** [Full trigger list — what you refuse to become]
+- **Current Ritual:** [Active daily ritual from Identity_Prime]
+
+---
+
+## 5.5 ACTIVE PATTERNS
+
+*Written by: `/analyse-day`, `/review-week`. Top patterns from Auto_Learnings.md at Confidence 3+. Light workflows read this instead of the full file.*
+
+- [PATTERN/CORRECTION] [Description] (Conf [X], [SEVERITY]) — Suggested: /[workflow]
+
+---
+
+## 6. ACTIVE SESSIONS (Rolling Buffer)
 
 *Written by: `/log` after each session. Rolling 5-entry buffer — newest at top, oldest drops off. Gives the next session instant context without reading 3 Daily Notes.*
 
@@ -64,7 +84,7 @@
 
 ---
 
-## 6. USER INJECTED CONTEXT (Brain Dump)
+## 7. USER INJECTED CONTEXT (Brain Dump)
 
 > **Instruction:** Use this section to dump anything on your mind. The AI will read this to understand your current state.
 
@@ -72,7 +92,7 @@
 
 ---
 
-## 7. BACKLOG (Sidequest Queue)
+## 8. BACKLOG (Sidequest Queue)
 
 > **Instruction:** Tasks that surface mid-session but don't belong on today's plan. `/plan-tomorrow` pulls from here. Never delete. Mark `[x]` when migrated to a Daily Note.
 
@@ -80,7 +100,7 @@
 
 ---
 
-## 7.5 COMMITMENTS (Outbound Promises)
+## 8.5 COMMITMENTS (Outbound Promises)
 
 > **Instruction:** Things YOU promised to someone else. Different from Waiting For (inbound). `/plan-tomorrow` checks for due dates. `/log` detects promises from conversation. Never delete. Mark `[x]` when fulfilled.
 
@@ -88,7 +108,7 @@
 
 ---
 
-## 8. SYSTEM PROTOCOLS (Agent Instructions)
+## 9. SYSTEM PROTOCOLS (Agent Instructions)
 
 **1. State Persistence:**
 *   Before starting any session, **READ THIS FILE**.

package/src/system/Mover_Global_Rules.md

@@ -17,6 +17,7 @@
 - [ ] I will actively `[[Link]]` Projects, Principles, and Strategies
 - [ ] I will cite sources for every claim: `[file:line]` or `[INFERRED: reason]`
 - [ ] **Engine file check:** At session end, flag any Engine files that changed and need version bump + commit.
+- [ ] **Active_Context loaded:** Read `02_Areas/Engine/Active_Context.md` NOW. This is the system's ephemeral state — blockers, tactical state, session history, active patterns. Do not wait for a workflow to load it.
 
 **Session Start:** Output `[Rules Loaded - DATE]` (e.g. `[Rules Loaded - 2026-02-20]`) to confirm date awareness.
 
@@ -89,16 +90,22 @@ Engine evolution: /history
 | ~~/init-plan~~ | DEPRECATED: merged into `/ignite` Section 12 | - |
 | ~~/project-notes~~ | DEPRECATED: merged into `/overview` Step 4 | - |
 
-**Memory Hierarchy (Load Order):**
+**Memory Hierarchy (Tiered Reads):**
+
+**Deep workflows** (analyse-day, review-week, plan-tomorrow, setup, update, ignite, pivot-strategy) read the full stack AND update Active_Context cache sections (Identity Snapshot, Active Patterns) after processing:
 
 | Priority | File | Purpose |
 |----------|------|---------|
 | P0 | Auto_Learnings.md | AI corrections & patterns |
-| P1 | Active_Context.md | Where are we NOW? |
+| P1 | Active_Context.md | Where are we NOW? (the cache layer) |
 | P2 | Strategy.md | What are we testing? |
 | P3 | Identity_Prime.md | Who are we? |
 | P4 | project_state.md | Project-specific context |
-| P5 | Today's Daily Note (if exists) + Yesterday's | Recent history. Today's note = live session context. |
+| P5 | Today's Daily Note (if exists) + Yesterday's | Recent history |
+
+**Light workflows** (log, morning, debrief, overview, harvest, reboot, refactor-plan, walkthrough, history) read Active_Context + targeted files only. Active_Context contains Identity Snapshot (S5), Active Patterns (S5.5), Strategic Verdict (S1), and Active Sessions (S6) — sufficient for most operations. This saves 8-16k tokens per invocation.
+
+**Freshness guarantee:** Deep workflows run daily (analyse-day every night, plan-tomorrow every morning). They update Active_Context's cache sections. If Active_Context is stale (>2 days), any workflow must flag it and suggest running `/analyse-day`.
 
 **AI Tooling (Platform Runtime):**
 
@@ -312,7 +319,7 @@ These triggers fire during EVERY conversation, not just workflows. **DETECT > WR
 |---------|---------------|---------------|
 | User reports action | "I did it", "just finished", "sent it", "got back from" | Daily Note `## Log` + mark `[x]` in plan.md if applicable |
 | Decision made | "Let's go with X", "I've decided", agreement on direction | Relevant file (plan.md, project_state.md, Active_Context) |
-| Commitment made | "I'll send", "I promised", "by Friday" | Active_Context `## 7.5 COMMITMENTS` |
+| Commitment made | "I'll send", "I promised", "by Friday" | Active_Context `## 8.5 COMMITMENTS` |
 | Waiting on someone | "He said he'd", "waiting on", "they'll get back to me" | Active_Context `## 3.5 WAITING FOR` |
 | Idea killed | "We're not doing X", "scrap that", "dead idea" | Active_Context `## 2. THE GRAVEYARD` |
 | URL/content pasted | Link to article, video, tweet, reel | Ask: "Capture to Library/Inputs?" then write on confirmation |

package/src/workflows/analyse-day.md

@@ -28,7 +28,7 @@ LOAD (Memory Hierarchy):
 5. Mover_Dossier.md (P3)
 6. Last 3 Daily Notes (P5) — yesterday + 2 days before, needed for multi-day pattern detection. Delegate reading to subagents (model: haiku) to keep main context clean. Extract: task completion rates, energy patterns, carry-over tasks, session log signals.
 7. Active project's `project_state.md` (P4) — get project path from Active_Context `## 4. TECHNICAL CONTEXT`. Read current phase, blockers, last milestone. Proactive load, not reactive.
-8. Active_Context `## 5. RECENT MEMORIES` / `## 5. ACTIVE SESSIONS` — rolling session buffer for operational context on recent work.
+8. Active_Context `## 6. ACTIVE SESSIONS` — rolling session buffer for operational context on recent work.
 
 CONSTRAINTS:
 - All verdicts grounded in log data, not assumptions
@@ -67,7 +67,7 @@ Read these files and extract the map:
 
 **From Strategy.md:** Primary Metric, Hypothesis, Daily Volume Targets, Variables, Constants.
 **From Identity_Prime.md:** Core Identity, Anti-Identity triggers, Non-negotiables.
-**From Active_Context.md:** Current project, phase, blockers, energy. Also read `## 5. RECENT MEMORIES` / `## 5. ACTIVE SESSIONS` for operational context on what was worked on across recent sessions.
+**From Active_Context.md:** Current project, phase, blockers, energy. Also read `## 6. ACTIVE SESSIONS` for operational context on what was worked on across recent sessions.
 **From Auto_Learnings.md:** Last 5 entries. Cross-reference with today's log.
 **From Daily Note:** Full content, especially Session Log and task list.
 
@@ -333,8 +333,10 @@ At end of analysis, propose Active_Context.md updates:
 3. Energy Level and trend (improving/declining/stable)
 4. Key decisions made today (if significant: create `03_Library/Entities/Decisions/[YYYY-MM-DD]-[Topic].md`)
 5. Any project scope changes or pivots
-6. Commitments check: "Did you promise anything to anyone today?" If yes, add to `## 7.5 COMMITMENTS`.
+6. Commitments check: "Did you promise anything to anyone today?" If yes, add to `## 8.5 COMMITMENTS`.
 7. Brain dump (ask: "Anything else on your mind before we close?")
+8. **Identity Snapshot (S5):** Refresh from Identity_Prime.md — Archetype, Core Drive, The Code (top 3), Anti-Identity (full triggers), Current Ritual. This is the cache that light workflows read instead of the full Identity file.
+9. **Active Patterns (S5.5):** Extract all patterns from Auto_Learnings.md at Confidence 3+. Format: `[PATTERN/CORRECTION] [Description] (Conf [X], [SEVERITY]) — Suggested: /[workflow]`. Light workflows read this instead of the full Auto_Learnings file.
 
 "Based on today's analysis, I'd like to update Active_Context.md with: [Changes]. Approve?"
 

package/src/workflows/debrief.md

@@ -21,9 +21,8 @@ git rev-parse --show-toplevel
 ```
 Save as VAULT_ROOT.
 
-LOAD (Memory Hierarchy):
-1. Active_Context.md (P1)
-2. Strategy.md (P2)
+LOAD (Light — Active_Context is the cache):
+1. Active_Context.md (has Strategic Verdict S1 for strategy context, Waiting For S3.5, Commitments S8.5)
 
 CONSTRAINTS:
 - All extractions must cite the source text
@@ -82,7 +81,7 @@ Anything YOU promised to deliver to someone. For each:
 - **To whom:** The person
 - **By when:** Deadline if stated
 
-→ Active_Context.md `## 7.5 COMMITMENTS`
+→ Active_Context.md `## 8.5 COMMITMENTS`
 
 ### 2D. Waiting For (Inbound Dependencies)
 
@@ -149,7 +148,7 @@ After confirmation, write each extraction to its destination:
 
 1. **Your actions** → Append to today's Daily Note `## Tasks` (or Active_Context Backlog if no Daily Note)
 2. **Waiting For** → Append to Active_Context.md `## 3.5 WAITING FOR`
-3. **Commitments** → Append to Active_Context.md `## 7.5 COMMITMENTS`
+3. **Commitments** → Append to Active_Context.md `## 8.5 COMMITMENTS`
 4. **Decisions** → Create `03_Library/Entities/Decisions/[YYYY-MM-DD]-[Topic].md`
 5. **People stubs** → Create `03_Library/Entities/People/[Name].md` (only if they don't already exist)
 6. **Key info** → Append to Daily Note `## Log`

package/src/workflows/debug-resistance.md

@@ -15,12 +15,11 @@ description: Debug psychological resistance through multi-step interrogation. Is
 
 Global Rules are pre-loaded as CLAUDE.md / GEMINI.md. Output `[Rules Loaded - DATE]`.
 
-LOAD:
-1. Auto_Learnings.md (P0 - check for recurring resistance patterns)
-2. Active_Context.md (P1)
-3. Strategy.md (P2)
-4. Identity_Prime.md (P3 - especially Anti-Identity)
-5. Today's Daily Note (if exists)
+LOAD (Light + Identity — Active_Context is the cache):
+1. Active_Context.md (has Active Patterns S5.5 for recurring patterns, Strategic Verdict S1, Identity Snapshot S5)
+2. Identity_Prime.md (FULL — needed for Step 4 Inversion: Anti-Identity specifics, evolved identity framing)
+3. Today's Daily Note (if exists)
+NOTE: Active Patterns S5.5 provides pattern check (Step 1). Identity_Prime is the exception — debug-resistance needs the full psychology file for the Inversion step, not just the snapshot. If Active_Context is stale (>2 days), flag it and suggest /analyse-day first.
 
 CONSTRAINTS:
 - Be direct but empathetic

package/src/workflows/harvest.md

@@ -16,10 +16,9 @@ description: Extract permanent knowledge from any source to Library. Classify, f
 
 Global Rules are pre-loaded as CLAUDE.md / GEMINI.md. Output `[Rules Loaded - DATE]`.
 
-LOAD:
-1. Auto_Learnings.md (P0)
-2. Active_Context.md (P1)
-3. The project's project_state.md (P4)
+LOAD (Light — Active_Context is the cache):
+1. Active_Context.md (has Active Patterns S5.5 for correction context)
+2. The project's project_state.md (P4 — Solutions Ledger is the primary harvest source)
 
 CONSTRAINTS:
 - Read Library directory headers BEFORE creating any new file [Mover_Global_Rules.md: S14]

package/src/workflows/log.md

@@ -41,12 +41,11 @@ Example: `{VAULT_ROOT}/02_Areas/Engine/Dailies/2026-02/Daily - 2026-02-20.md`
 NOTE: Daily notes are in MONTH SUBFOLDERS, not in `Dailies/` root. Never search `Dailies/Daily - *.md` directly.
 NOTE: Always use VAULT_ROOT prefix. You may be inside a project subdirectory — relative paths will resolve wrong.
 
-LOAD (Memory Hierarchy):
-1. Auto_Learnings.md (P0)
-2. Active_Context.md (P1)
-3. Strategy.md (P2)
-4. Identity_Prime.md (P3 - summary)
-5. Yesterday's Daily Note (P5) — 1 note sufficient for session context
+LOAD (Light — Active_Context is the cache):
+1. Active_Context.md (has Identity Snapshot S5, Active Patterns S5.5, Strategic Verdict S1, Active Sessions S6)
+2. Today's Daily Note
+3. Active project's plan.md (for task sync)
+4. Auto_Learnings.md — ONLY if Step 10 triggers (user correction detected). Do NOT pre-load.
 
 CONSTRAINTS:
 - All claims grounded in session history or source files
@@ -107,7 +106,7 @@ Scan the entire conversation. Extract:
 7. **Sidequest Tasks:** Any "need to," "should," "want to" tasks mentioned but NOT on today's plan. These go to Active_Context.md `## 8. BACKLOG`.
 8. **Waiting For:** Any "waiting on [person]," "sent to [name]," "DM'd/emailed [X]" — extract and add to Active_Context.md `## 3.5 WAITING FOR` with estimated date if mentioned.
 9. **Someday/Maybe:** Any "one day I'd like to," "could be interesting," "not now but maybe" — add to `02_Areas/Engine/Someday_Maybe.md` under the appropriate section.
-10. **Commitments:** Any "I'll send," "I promised," "I told [name] I would," "by [day]" — outbound promises to others. These go to Active_Context.md `## 7.5 COMMITMENTS`.
+10. **Commitments:** Any "I'll send," "I promised," "I told [name] I would," "by [day]" — outbound promises to others. These go to Active_Context.md `## 8.5 COMMITMENTS`.
 11. **Decisions:** Any major decision made this session (strategy change, tool choice, architectural call, commitment to a direction). Create a note in `03_Library/Entities/Decisions/` using the template. Only for significant calls, not micro-decisions.
 12. **Reading/Input:** Any "I read," "I watched," "I listened to," content pasted from articles/books/threads — capture source and key takeaway to `03_Library/Inputs/` (Articles/, Books/, or Videos/ subfolder using templates).
 13. **Plan Overrides:** Any moment where the user worked on something that contradicted today's plan, Single Test, or Sacrifice. Log as: `[OVERRIDE] User chose [what] over [plan item]. Reason: "[stated reason or NONE if no reason given]"`. Count total overrides. `/analyse-day` uses these to score strategic alignment.
@@ -222,14 +221,14 @@ If no project_state.md in scope: skip this step.
 
 **Someday/Maybe** (Step 3.9 items): Append to `02_Areas/Engine/Someday_Maybe.md` under the correct section.
 
-**Commitments** (Step 3.10 items): Append to Active_Context.md `## 7.5 COMMITMENTS`:
+**Commitments** (Step 3.10 items): Append to Active_Context.md `## 8.5 COMMITMENTS`:
 `- [ ] [What you promised] — [To: name] — [Due by: date or TBD] — [Added: YYYY-MM-DD]`
 
 **Decisions** (Step 3.11 items): Create `03_Library/Entities/Decisions/[YYYY-MM-DD]-[Topic].md` using the Decisions template. Fill: Decision, Context, Alternatives Considered, Reasoning. Leave Outcome Tracking for future review.
 
 **Reading** (Step 3.12 items): Create note in `03_Library/Inputs/Articles/` (or Books/Videos/) using the subfolder template. Fill: Source, Author, Key Takeaways. Add `> **Up:** [[Inputs MOC]]`.
 
-**Active Sessions** buffer: Prepend a 1-line summary to Active_Context.md `## 5. ACTIVE SESSIONS`:
+**Active Sessions** buffer: Prepend a 1-line summary to Active_Context.md `## 6. ACTIVE SESSIONS`:
 `* **[YYYY-MM-DD HH:MM]:** [1-line session summary — what was done, key outcome]`
 Keep only the 5 most recent entries. If > 5: remove the oldest.
 

package/src/workflows/morning.md

@@ -16,12 +16,10 @@ description: Quick primer to start a work session. Read Identity, set Single Tes
 
 Global Rules are pre-loaded as CLAUDE.md / GEMINI.md. Output `[Rules Loaded - DATE]`.
 
-LOAD (Memory Hierarchy):
-1. Auto_Learnings.md (P0 - last 3 entries)
-2. Active_Context.md (P1)
-3. Strategy.md (P2)
-4. Identity_Prime.md (P3)
-5. Today's Daily Note (if exists)
+LOAD (Light — Active_Context is the cache):
+1. Active_Context.md (has Identity Snapshot S5, Active Patterns S5.5, Strategic Verdict S1, Active Sessions S6)
+2. Today's Daily Note (if exists)
+NOTE: Identity Snapshot in Active_Context S5 provides Archetype, Core Drive, Anti-Identity, and Ritual for the morning prime. Active Patterns S5.5 provides pattern alerts. Strategic Verdict S1 provides the Primary Metric for Single Test. If Active_Context is stale (>2 days), flag it and suggest /analyse-day first.
 
 CONSTRAINTS:
 - Keep this fast: 5 minutes max

package/src/workflows/overview.md

@@ -15,12 +15,10 @@ description: Project context refresh. Shows current state, processes notes, flag
 
 Global Rules are pre-loaded as CLAUDE.md / GEMINI.md. Output `[Rules Loaded - DATE]`.
 
-LOAD (Memory Hierarchy):
-1. Auto_Learnings.md (P0)
-2. Active_Context.md (P1)
-3. Strategy.md (P2)
-4. Identity_Prime.md (P3 - summary)
-5. Yesterday's Daily Note (P5) — 1 note sufficient for project context
+LOAD (Light — Active_Context is the cache):
+1. Active_Context.md (has Strategic Verdict S1, Technical Context S4, Active Sessions S6)
+2. Active project's plan.md, project_state.md, project_brief.md (Step 2 reads)
+NOTE: Strategy context comes from Active_Context S1. If Active_Context is stale (>2 days), flag it and suggest /analyse-day first.
 
 CONSTRAINTS:
 - All claims grounded in project files

package/src/workflows/plan-tomorrow.md

@@ -27,7 +27,7 @@ LOAD (Memory Hierarchy):
 6. Goals.md (if exists)
 7. Last 3-5 Daily Notes (P5)
 8. Active project's `project_state.md` (P4) — get project path from Active_Context `## 4. TECHNICAL CONTEXT`. Read current phase, blockers, last milestone from Solutions Ledger and Changelog. Skip if no active project.
-9. Active_Context `## 5. RECENT MEMORIES` / `## 5. ACTIVE SESSIONS` — rolling session buffer for operational awareness of recent work across sessions.
+9. Active_Context `## 6. ACTIVE SESSIONS` — rolling session buffer for operational awareness of recent work across sessions.
 
 CONSTRAINTS:
 - All task selections grounded in Strategy.md or Identity_Prime.md
@@ -99,7 +99,7 @@ Every single incomplete task MUST appear in tomorrow's plan unless the user expl
 Do NOT silently drop tasks. If a task was planned and not done, it carries forward with a carry count: `(x2)`, `(x3)`, etc.
 
 ### 3B. Backlog Sweep
-Read Active_Context.md `## 7. BACKLOG` section. Any unchecked `[ ]` items? Pull them into tomorrow's task list. Mark them `[x]` in Active_Context after migration. Note source in the Daily Note: "(from Backlog)".
+Read Active_Context.md `## 8. BACKLOG` section. Any unchecked `[ ]` items? Pull them into tomorrow's task list. Mark them `[x]` in Active_Context after migration. Note source in the Daily Note: "(from Backlog)".
 
 ### 3B.5 Waiting For Check
 Read Active_Context.md `## 3.5 WAITING FOR` section. Any items where "Expected by" date is tomorrow or earlier?
@@ -107,7 +107,7 @@ Read Active_Context.md `## 3.5 WAITING FOR` section. Any items where "Expected b
 - Add a follow-up task to the plan if the item is overdue and actionable.
 
 ### 3C. Commitments Check
-Read Active_Context.md `## 7.5 COMMITMENTS` section. Any items where "Due by" date is tomorrow or earlier?
+Read Active_Context.md `## 8.5 COMMITMENTS` section. Any items where "Due by" date is tomorrow or earlier?
 - Flag due items: "COMMITMENT DUE: You promised [X] to [person] by [date]. Add to plan?"
 - Add a task to the plan for due commitments. These are promises to people, not optional.
 

package/src/workflows/primer.md

@@ -16,12 +16,10 @@ description: Quick primer to start a work session. Read Identity, set Single Tes
 
 Global Rules are pre-loaded as CLAUDE.md / GEMINI.md. Output `[Rules Loaded - DATE]`.
 
-LOAD (Memory Hierarchy):
-1. Auto_Learnings.md (P0 - last 3 entries)
-2. Active_Context.md (P1)
-3. Strategy.md (P2)
-4. Identity_Prime.md (P3)
-5. Today's Daily Note (if exists)
+LOAD (Light — Active_Context is the cache):
+1. Active_Context.md (has Identity Snapshot S5, Active Patterns S5.5, Strategic Verdict S1, Active Sessions S6)
+2. Today's Daily Note (if exists)
+NOTE: Identity Snapshot in Active_Context S5 provides Archetype, Core Drive, Anti-Identity, and Ritual for the morning prime. Active Patterns S5.5 provides pattern alerts. Strategic Verdict S1 provides the Primary Metric for Single Test. If Active_Context is stale (>2 days), flag it and suggest /analyse-day first.
 
 CONSTRAINTS:
 - Keep this fast: 5 minutes max

package/src/workflows/reboot.md

@@ -15,12 +15,10 @@ description: Emergency reboot when logs are stale (3+ days missing). Diagnose +
 
 Global Rules are pre-loaded as CLAUDE.md / GEMINI.md. Output `[Rules Loaded - DATE]`.
 
-LOAD:
-1. Auto_Learnings.md (P0 - check for recurring reboot patterns)
-2. Active_Context.md (P1)
-3. Strategy.md (P2 - current metric and primary task)
-4. Identity_Prime.md (P3)
-5. Last Daily Note (whenever it was)
+LOAD (Light — Active_Context is the cache):
+1. Active_Context.md (has Active Patterns S5.5 for recurring reboot patterns, Strategic Verdict S1 for primary metric, Identity Snapshot S5)
+2. Last Daily Note (whenever it was)
+NOTE: Active Patterns S5.5 provides reboot pattern check (Step 1). Strategic Verdict S1 provides primary metric for Step 4 prescription. If Active_Context is stale (>7 days), Step 6 will propose a rebuild. No need to pre-load Strategy or Identity — the cache is sufficient for emergency recovery.
 
 CONSTRAINTS:
 - This must be FAST. Under 15 minutes total.

package/src/workflows/refactor-plan.md

@@ -17,12 +17,12 @@ In V4, this is typically triggered by the system (after `/pivot-strategy` or whe
 
 Global Rules are pre-loaded as CLAUDE.md / GEMINI.md. Output `[Rules Loaded - DATE]`.
 
-LOAD:
-1. Auto_Learnings.md (P0 - check for recurring plan drift patterns)
-2. Active_Context.md (P1)
-3. Strategy.md (P2)
-4. Current plan.md (READ ONLY first)
-5. project_state.md (for changelog)
+LOAD (Light + Strategy — Active_Context is the cache):
+1. Active_Context.md (has Active Patterns S5.5 for plan drift patterns, Strategic Verdict S1)
+2. Strategy.md (FULL — needed for direct comparison: plan.md Architecture vs Strategy.md targets)
+3. Current plan.md (READ ONLY first)
+4. project_state.md (for changelog)
+NOTE: Strategy.md is the exception — refactor-plan compares plan.md against Strategy.md changes directly. Active Patterns S5.5 provides drift pattern history. If Active_Context is stale (>2 days), flag it and suggest /analyse-day first.
 
 CONSTRAINTS:
 - SURGICAL EDITING. Never rewrite the entire file.

package/src/workflows/review-week.md

@@ -367,9 +367,11 @@ Always runs — Active_Context is always stale after a week.
 3. Update "Current Phase" if shifted
 4. Section 2 (Graveyard): if any ideas were killed this week (from Inbox triage, Someday/Maybe pruning, or user decisions), add them here with reason and date
 5. Section 4 (Technical Context): if active project changed, update project name, path, and tech stack
-6. Section 5 (Active Sessions): verify buffer is current — trim to last 5 entries
+6. Section 6 (Active Sessions): verify buffer is current — trim to last 5 entries
 7. Write workflow state: `weekly_review_last_run: [YYYY-MM-DD]`
 8. If MONTHLY_MODE was true: also write `monthly_review_last_run: [YYYY-MM-DD]` to Workflow State
+9. **Identity Snapshot (S5):** Refresh from Identity_Prime.md — Archetype, Core Drive, The Code (top 3), Anti-Identity (full triggers), Current Ritual. This is the cache that light workflows read instead of the full Identity file.
+10. **Active Patterns (S5.5):** Extract all patterns from Auto_Learnings.md at Confidence 3+. Format: `[PATTERN/CORRECTION] [Description] (Conf [X], [SEVERITY]) — Suggested: /[workflow]`. Light workflows read this instead of the full Auto_Learnings file.
 
 "Proposed Active_Context.md changes:
 [DIFF FORMAT — only the lines that change, not the full file]

package/src/workflows/update.md

@@ -23,8 +23,9 @@ Save as VAULT_ROOT.
 
 LOAD (Memory Hierarchy):
 1. Auto_Learnings.md (P0)
-2. Active_Context.md (P1) — read `## My Customizations` to understand what the user has changed. NEVER overwrite any workflow or rule that appears in this log.
+2. Active_Context.md (P1) — read `## My Customizations` to understand what the user has changed. NEVER overwrite any workflow or rule that appears in this log. Also note current section structure (section numbers, headings) to detect renaming needs.
 3. Identity_Prime.md (P3 — needed for migration gap detection)
+4. Daily_Template.md — check for new sections (Food Log, Sleep Log) that may need adding
 
 CONSTRAINTS:
 - NEVER overwrite existing Engine file content
@@ -142,6 +143,15 @@ Read the file. Check for:
 | `analyse_day_last_run` | V4.5 | Contains this key? |
 | `log_last_run` | V4.5 | Contains this key? |
 | `review_week_day` | V4 | Contains this key? |
+| `setup_date` | V4.7 | Contains this key in Workflow State? |
+| `monthly_review_last_run` | V4.7 | Contains this key in Workflow State? |
+| WAITING FOR section (S3.5) | V4.7 | Contains "WAITING FOR" heading? |
+| Identity Snapshot section (S5) | V4.7 | Contains "IDENTITY SNAPSHOT" heading? |
+| Active Patterns section (S5.5) | V4.7 | Contains "ACTIVE PATTERNS" heading? |
+| ACTIVE SESSIONS (was RECENT MEMORIES) | V4.7 | Contains "RECENT MEMORIES" heading? (needs rename) |
+| Backlog section (S8) | V4.7 | Contains "BACKLOG" heading? |
+| Commitments section (S8.5) | V4.7 | Contains "COMMITMENTS" heading? |
+| My Customizations section | V4.7 | Contains "My Customizations" heading? |
 
 ### 3C. Strategy.md
 
@@ -264,6 +274,118 @@ WAIT FOR CONFIRMATION.
 Append `review_week_day: [answer]` to the Workflow State section.
 WAIT FOR CONFIRMATION.
 
+### 5I. Waiting For Section (if missing in Active_Context.md)
+
+No interview needed — structural section. Append after Section 3 (TACTICAL STATE):
+
+```markdown
+## 3.5 WAITING FOR
+
+> **Instruction:** Things you've delegated or that depend on someone else. `/plan-tomorrow` checks this and flags anything overdue. Never delete — mark `[x]` when resolved.
+
+```
+
+"Adding 'Waiting For' section to Active_Context.md — tracks things you're waiting on from other people."
+WAIT FOR CONFIRMATION.
+
+### 5J. Identity Snapshot (if missing in Active_Context.md)
+
+No interview needed — populated automatically by `/analyse-day` and `/review-week`. Append after Section 4:
+
+```markdown
+## 5. IDENTITY SNAPSHOT
+
+*Written by: `/analyse-day`, `/review-week`, `/setup`. Condensed from Identity_Prime.md. Light workflows read this instead of the full file.*
+
+- **Archetype:** [Run /analyse-day to populate]
+- **Core Drive:** [Run /analyse-day to populate]
+- **The Code:** [Run /analyse-day to populate]
+- **Anti-Identity:** [Run /analyse-day to populate]
+- **Current Ritual:** [Run /analyse-day to populate]
+```
+
+"Adding Identity Snapshot cache to Active_Context.md. This gets populated by `/analyse-day` so light workflows don't need to read the full Identity file."
+WAIT FOR CONFIRMATION.
+
+### 5K. Active Patterns (if missing in Active_Context.md)
+
+No interview needed — populated automatically by `/analyse-day` and `/review-week`. Append after Identity Snapshot:
+
+```markdown
+## 5.5 ACTIVE PATTERNS
+
+*Written by: `/analyse-day`, `/review-week`. Top patterns from Auto_Learnings.md at Confidence 3+. Light workflows read this instead of the full file.*
+
+- [Run /analyse-day to populate from Auto_Learnings.md]
+```
+
+"Adding Active Patterns cache. Gets populated automatically from your Auto_Learnings.md."
+WAIT FOR CONFIRMATION.
+
+### 5L. RECENT MEMORIES → ACTIVE SESSIONS Rename (if old heading found)
+
+If the file contains `## 5. RECENT MEMORIES` or any heading with "RECENT MEMORIES":
+
+Rename to `## 6. ACTIVE SESSIONS (Rolling Buffer)`. Keep ALL existing content under the section.
+
+"Renaming 'Recent Memories' to 'Active Sessions' — same content, clearer name, new section number to make room for Identity Snapshot and Active Patterns above."
+WAIT FOR CONFIRMATION.
+
+### 5M. Backlog Section (if missing in Active_Context.md)
+
+No interview needed — structural section. Append:
+
+```markdown
+## 8. BACKLOG (Sidequest Queue)
+
+> **Instruction:** Tasks that surface mid-session but don't belong on today's plan. `/plan-tomorrow` pulls from here. Never delete. Mark `[x]` when migrated to a Daily Note.
+
+```
+
+"Adding Backlog section — a parking lot for tasks that surface mid-session."
+WAIT FOR CONFIRMATION.
+
+### 5N. Commitments Section (if missing in Active_Context.md)
+
+No interview needed — structural section. Append:
+
+```markdown
+## 8.5 COMMITMENTS (Outbound Promises)
+
+> **Instruction:** Things YOU promised to someone else. Different from Waiting For (inbound). `/plan-tomorrow` checks for due dates. `/log` detects promises from conversation. Never delete. Mark `[x]` when fulfilled.
+
+```
+
+"Adding Commitments section — tracks promises you've made to others."
+WAIT FOR CONFIRMATION.
+
+### 5O. My Customizations Section (if missing in Active_Context.md)
+
+No interview needed — structural tracking section. Append:
+
+```markdown
+## My Customizations (Permanent Log)
+
+> **Instruction:** Track your personal modifications to Mover OS here. The `/update` workflow reads this to avoid overwriting your customizations. Append-only — never delete.
+
+| Date | File Modified | What Changed | Why |
+| :--- | :--- | :--- | :--- |
+| | | | |
+```
+
+"Adding My Customizations log — this protects your personal modifications from being overwritten in future updates."
+WAIT FOR CONFIRMATION.
+
+### 5P. Workflow State Keys (if missing keys in existing Workflow State)
+
+No interview needed. Add any missing keys to the existing Workflow State code block:
+
+- `setup_date: [unknown]` (if missing)
+- `monthly_review_last_run:` (if missing)
+
+"Adding missing timestamp keys to your Workflow State section."
+WAIT FOR CONFIRMATION.
+
 ### 5D. Goals.md (if file missing entirely)
 
 "V4 added a Goals file. Let me derive your goals from your existing Identity and Strategy."

package/src/workflows/walkthrough.md

@@ -16,11 +16,9 @@ description: Guided tour of Mover OS after setup. Explains system, folders, work
 
 Global Rules are pre-loaded as CLAUDE.md / GEMINI.md. Output `[Rules Loaded - DATE]`.
 
-LOAD (Memory Hierarchy):
-1. Auto_Learnings.md (P0 - last 3 entries)
-2. Active_Context.md (P1 - current state for personalization)
-3. Identity_Prime.md (P3 - to personalize the tour)
-4. Strategy.md (P2 - to reference their goals)
+LOAD (Light — Active_Context is the cache):
+1. Active_Context.md (has Identity Snapshot S5 for personalization, Strategic Verdict S1 for goals, Active Patterns S5.5)
+NOTE: Identity Snapshot S5 provides Archetype and Core Drive for personalizing examples. Strategic Verdict S1 provides current strategy for goal references. No need for full Identity/Strategy files — the tour needs context, not depth. If Active_Context is stale (>2 days), flag it and suggest /analyse-day first.
 
 CONSTRAINTS:
 - Personalize all examples to user's Identity and Strategy