moveros 4.0.8 → 4.1.0

package/src/workflows/reboot.md

@@ -1,201 +1,201 @@
----
-description: Emergency reboot when logs are stale (3+ days missing). Diagnose + Act in same session.
----
-
-# Emergency Reboot (V4)
-
-**Trigger:** User runs `/reboot` OR system detects 3+ days of stale logs.
-**Role:** Emergency Recovery Agent.
-**Task:** Break through the Wall of Shame. Diagnose + Act in under 15 minutes.
-**Risk Tier:** LOW (just get moving)
-
----
-
-## 0. PRE-FLIGHT
-
-Global Rules are pre-loaded as CLAUDE.md / GEMINI.md. Output `[Rules Loaded - DATE]`.
-
-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 3 Daily Notes (P5) — not just the most recent. Reading 3 shows the trajectory leading into the gap: was output declining? Was there a trigger event? Was sleep or energy deteriorating? Read via subagent (model: haiku) to keep main context clean.
-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.
-- No lengthy analysis. That's for /analyse-day.
-- One question, one action. Get moving.
-
----
-
-## 1. STALENESS ASSESSMENT
-
-Calculate: How many days since last Daily Note?
-
-| Days | Severity | Approach |
-|------|----------|----------|
-| 3-5 | Mild | Standard reboot |
-| 6-14 | Moderate | Extended context recovery |
-| 14+ | Severe | Full Active_Context rebuild |
-
-If severe: "You've been away [X] days. Let's not dwell on it. Forward only."
-
-Check Auto_Learnings: Is this a recurring reboot pattern?
-If yes: "This is reboot #[X]. The pattern is real. Let's address why this keeps happening AFTER we get you moving."
-
----
-
-## 2. QUICK DIAGNOSTIC (2 min)
-
-ONE question:
-"What am I resisting right now?"
-
-Have them write it down. One sentence. Examples:
-- "I'm afraid of rejection."
-- "I don't believe the offer works."
-- "I don't want to start."
-- "I don't even know where I was."
-
-If answer is "I don't know":
-- Read the last Daily Note's Single Test.
-- "Your last Single Test was [X]. Is that still relevant?"
-
----
-
-## 3. CONTEXT RECOVERY
-
-Quick scan of last known state:
-- From Strategy.md: What's the primary task?
-- From last 3 Daily Notes: What was the trajectory? Was output declining? What was the last Single Test? Were there signs of an incoming gap (sleep deteriorating, energy dropping, avoidance patterns)?
-- From Active_Context.md: What were the blockers?
-
-Summarize: "Here's where you left off: [Project], [Phase], [Last task]. The primary metric is [X]."
-
-If trajectory shows a pattern (e.g., 3 consecutive days of declining deep work hours, or repeated task carry-over before the gap): surface it. "Before the gap, I can see [pattern] across your last 3 sessions. That context matters for the reboot."
-
----
-
-## 4. PRESCRIBE THE ACTION
-
-Based on Strategy.md primary task, prescribe a Minimum Viable Action:
-
-| Primary Task | Minimum Viable Action |
-|---|---|
-| DMs / Outreach | Find 1 lead, send 1 DM |
-| Content Creation | Record 1 video (60s, no editing) |
-| Coding / Building | Write 1 function or fix 1 bug |
-| Sales Calls | Make 1 call or send 1 follow-up |
-| Writing | Write 1 paragraph |
-
-**The Rule:** Completable in under 15 minutes. No setup. No systems. Raw action.
-
-"Your Primary Task is [X]. The Minimum Viable Action is [Y]. Do it NOW. 15 minutes."
-
-**STOP. Wait for user to complete the action and report back. Do NOT proceed to Step 5 until user confirms they have taken action.**
-
----
-
-## 5. LOG (Post-Action Only)
-
-**Only runs after user confirms action taken.** Update or create today's Daily Note:
-
-```markdown
-## Session Log
-
-### [TIME] - REBOOT EXECUTED
-System reboot after [X] days inactive. Resistance: [User's answer].
-Action Taken: [Yes/No]. What: [Description].
-Energy: [Inferred]. Next: Resume normal workflow.
-```
-
----
-
-## 6. ACTIVE_CONTEXT UPDATE
-
-If Active_Context is stale (>7 days), propose quick update:
-- Current Project
-- Current Phase
-- Main Blocker
-- Energy Level
-
-"I'd like to update Active_Context.md. Approve these changes?"
-
----
-
-## 7. ESCALATION LADDER
-
-| Reboot # | Trigger | Action |
-|---|---|---|
-| 1 | 3+ days stale | This protocol (self-directed) |
-| 2 | Failed Reboot 1 | AI prompts user to contact accountability partner. Draft the message together if needed. |
-| 3 | Failed Reboot 2 | Agree with user to a specific external commitment (public, logged in Auto_Learnings) before AI continues planning. |
-
-Track reboot count in Auto_Learnings.md if this becomes a pattern.
-
----
-
-## THE LOCK RULE
-
-If the user attempts to run `/analyse-day` or `/plan-tomorrow` before completing the reboot action, remind them:
-"The reboot action isn't confirmed yet. Complete it first — even a partial attempt counts. Report back when done."
-
-This is a conversational gate, not a system lock. The AI reminds and redirects.
-
----
-
-## 8. SELF-VERIFICATION (CISC)
-
-Before outputting the prescription, self-check:
-1. Staleness assessment grounded in actual Daily Note dates? (90%+ accuracy)
-2. Minimum Viable Action directly derived from Strategy.md primary task?
-3. Context recovery summary accurate to last known state in files?
-4. No generic advice — every recommendation tied to user's specific files?
-
-If any section < 90% confident: flag it explicitly before prescribing.
-
----
-
-## 9. ANSWER GATING
-
-Do not suggest handoff until:
-- User has stated their resistance (Section 2 completed).
-- User has confirmed they will attempt the Minimum Viable Action.
-
-If pending: "You haven't committed to an action yet. What's the one thing you'll do in the next 15 minutes?"
-
----
-
-## 10. PROACTIVE SUGGESTIONS
-
-Based on observations during this workflow:
-1. [If Auto_Learnings shows 3+ reboot events] - Confidence: [X] - "This is a systemic pattern. Consider `/debug-resistance` to address root cause after getting moving."
-2. [If Active_Context is severely stale (14+ days)] - Confidence: [X] - "Run `/overview` on active projects after this reboot to recover full context."
-3. [If Strategy.md primary task changed since last Daily Note] - Confidence: [X] - "Your strategy may have shifted. Verify alignment before committing to action."
-
-"Want me to address any of these?"
-
----
-
-## 11. SELF-IMPROVEMENT
-
-If user corrected AI during this workflow:
-1. Acknowledge: "I made a mistake."
-2. Identify the rule violated.
-3. Append to Auto_Learnings.md:
-   `* [YYYY-MM-DD] CORRECTION: [Description]. Source: User correction. Confidence: 3.`
-4. If same correction seen 3x+, escalate confidence to 5.
-
----
-
-## HANDOFF
-
-Sources used: Auto_Learnings.md, Active_Context.md, Strategy.md, Identity_Prime.md, Last Daily Note
-Confidence range: [X-Y across outputs]
-
-**Next:** "Reboot complete. Now run `/analyse-day` to get back on track, then `/plan-tomorrow` for a fresh plan."
-
-If severe (14+ days): "Consider running `/overview` on your active projects first to refresh context."
-
-Key rules still active:
-- All claims must be grounded in source files
-- Confidence < 3 = ask, don't assert
-- Append-only: never delete from Auto_Learnings.md or Daily Notes
+---
+description: Emergency reboot when logs are stale (3+ days missing). Diagnose + Act in same session.
+---
+
+# Emergency Reboot (V4)
+
+**Trigger:** User runs `/reboot` OR system detects 3+ days of stale logs.
+**Role:** Emergency Recovery Agent.
+**Task:** Break through the Wall of Shame. Diagnose + Act in under 15 minutes.
+**Risk Tier:** LOW (just get moving)
+
+---
+
+## 0. PRE-FLIGHT
+
+Global Rules are pre-loaded as CLAUDE.md / GEMINI.md. Output `[Rules Loaded - DATE]`.
+
+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 3 Daily Notes (P5) — not just the most recent. Reading 3 shows the trajectory leading into the gap: was output declining? Was there a trigger event? Was sleep or energy deteriorating? Read via subagent (model: haiku) to keep main context clean.
+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.
+- No lengthy analysis. That's for /analyse-day.
+- One question, one action. Get moving.
+
+---
+
+## 1. STALENESS ASSESSMENT
+
+Calculate: How many days since last Daily Note?
+
+| Days | Severity | Approach |
+|------|----------|----------|
+| 3-5 | Mild | Standard reboot |
+| 6-14 | Moderate | Extended context recovery |
+| 14+ | Severe | Full Active_Context rebuild |
+
+If severe: "You've been away [X] days. Let's not dwell on it. Forward only."
+
+Check Auto_Learnings: Is this a recurring reboot pattern?
+If yes: "This is reboot #[X]. The pattern is real. Let's address why this keeps happening AFTER we get you moving."
+
+---
+
+## 2. QUICK DIAGNOSTIC (2 min)
+
+ONE question:
+"What am I resisting right now?"
+
+Have them write it down. One sentence. Examples:
+- "I'm afraid of rejection."
+- "I don't believe the offer works."
+- "I don't want to start."
+- "I don't even know where I was."
+
+If answer is "I don't know":
+- Read the last Daily Note's Single Test.
+- "Your last Single Test was [X]. Is that still relevant?"
+
+---
+
+## 3. CONTEXT RECOVERY
+
+Quick scan of last known state:
+- From Strategy.md: What's the primary task?
+- From last 3 Daily Notes: What was the trajectory? Was output declining? What was the last Single Test? Were there signs of an incoming gap (sleep deteriorating, energy dropping, avoidance patterns)?
+- From Active_Context.md: What were the blockers?
+
+Summarize: "Here's where you left off: [Project], [Phase], [Last task]. The primary metric is [X]."
+
+If trajectory shows a pattern (e.g., 3 consecutive days of declining deep work hours, or repeated task carry-over before the gap): surface it. "Before the gap, I can see [pattern] across your last 3 sessions. That context matters for the reboot."
+
+---
+
+## 4. PRESCRIBE THE ACTION
+
+Based on Strategy.md primary task, prescribe a Minimum Viable Action:
+
+| Primary Task | Minimum Viable Action |
+|---|---|
+| DMs / Outreach | Find 1 lead, send 1 DM |
+| Content Creation | Record 1 video (60s, no editing) |
+| Coding / Building | Write 1 function or fix 1 bug |
+| Sales Calls | Make 1 call or send 1 follow-up |
+| Writing | Write 1 paragraph |
+
+**The Rule:** Completable in under 15 minutes. No setup. No systems. Raw action.
+
+"Your Primary Task is [X]. The Minimum Viable Action is [Y]. Do it NOW. 15 minutes."
+
+**STOP. Wait for user to complete the action and report back. Do NOT proceed to Step 5 until user confirms they have taken action.**
+
+---
+
+## 5. LOG (Post-Action Only)
+
+**Only runs after user confirms action taken.** Update or create today's Daily Note:
+
+```markdown
+## Session Log
+
+### [TIME] - REBOOT EXECUTED
+System reboot after [X] days inactive. Resistance: [User's answer].
+Action Taken: [Yes/No]. What: [Description].
+Energy: [Inferred]. Next: Resume normal workflow.
+```
+
+---
+
+## 6. ACTIVE_CONTEXT UPDATE
+
+If Active_Context is stale (>7 days), propose quick update:
+- Current Project
+- Current Phase
+- Main Blocker
+- Energy Level
+
+"I'd like to update Active_Context.md. Approve these changes?"
+
+---
+
+## 7. ESCALATION LADDER
+
+| Reboot # | Trigger | Action |
+|---|---|---|
+| 1 | 3+ days stale | This protocol (self-directed) |
+| 2 | Failed Reboot 1 | AI prompts user to contact accountability partner. Draft the message together if needed. |
+| 3 | Failed Reboot 2 | Agree with user to a specific external commitment (public, logged in Auto_Learnings) before AI continues planning. |
+
+Track reboot count in Auto_Learnings.md if this becomes a pattern.
+
+---
+
+## THE LOCK RULE
+
+If the user attempts to run `/analyse-day` or `/plan-tomorrow` before completing the reboot action, remind them:
+"The reboot action isn't confirmed yet. Complete it first — even a partial attempt counts. Report back when done."
+
+This is a conversational gate, not a system lock. The AI reminds and redirects.
+
+---
+
+## 8. SELF-VERIFICATION (CISC)
+
+Before outputting the prescription, self-check:
+1. Staleness assessment grounded in actual Daily Note dates? (90%+ accuracy)
+2. Minimum Viable Action directly derived from Strategy.md primary task?
+3. Context recovery summary accurate to last known state in files?
+4. No generic advice — every recommendation tied to user's specific files?
+
+If any section < 90% confident: flag it explicitly before prescribing.
+
+---
+
+## 9. ANSWER GATING
+
+Do not suggest handoff until:
+- User has stated their resistance (Section 2 completed).
+- User has confirmed they will attempt the Minimum Viable Action.
+
+If pending: "You haven't committed to an action yet. What's the one thing you'll do in the next 15 minutes?"
+
+---
+
+## 10. PROACTIVE SUGGESTIONS
+
+Based on observations during this workflow:
+1. [If Auto_Learnings shows 3+ reboot events] - Confidence: [X] - "This is a systemic pattern. Consider `/debug-resistance` to address root cause after getting moving."
+2. [If Active_Context is severely stale (14+ days)] - Confidence: [X] - "Run `/overview` on active projects after this reboot to recover full context."
+3. [If Strategy.md primary task changed since last Daily Note] - Confidence: [X] - "Your strategy may have shifted. Verify alignment before committing to action."
+
+"Want me to address any of these?"
+
+---
+
+## 11. SELF-IMPROVEMENT
+
+If user corrected AI during this workflow:
+1. Acknowledge: "I made a mistake."
+2. Identify the rule violated.
+3. Append to Auto_Learnings.md:
+   `* [YYYY-MM-DD] CORRECTION: [Description]. Source: User correction. Confidence: 3.`
+4. If same correction seen 3x+, escalate confidence to 5.
+
+---
+
+## HANDOFF
+
+Sources used: Auto_Learnings.md, Active_Context.md, Strategy.md, Identity_Prime.md, Last Daily Note
+Confidence range: [X-Y across outputs]
+
+**Next:** "Reboot complete. Now run `/analyse-day` to get back on track, then `/plan-tomorrow` for a fresh plan."
+
+If severe (14+ days): "Consider running `/overview` on your active projects first to refresh context."
+
+Key rules still active:
+- All claims must be grounded in source files
+- Confidence < 3 = ask, don't assert
+- Append-only: never delete from Auto_Learnings.md or Daily Notes