moveros 4.0.8 → 4.1.0

package/src/workflows/debug-resistance.md

@@ -1,180 +1,180 @@
----
-description: Debug psychological resistance through multi-step interrogation. Isolate, map, invert, prove.
----
-
-# Debug Resistance (V4)
-
-**Trigger:** User says "I'm stuck," "I'm procrastinating," or `/debug-resistance`
-**Role:** Paradigm Surgeon.
-**Task:** Diagnose and dismantle the psychological block preventing execution.
-**Risk Tier:** LOW
-
----
-
-## 0. PRE-FLIGHT
-
-Global Rules are pre-loaded as CLAUDE.md / GEMINI.md. Output `[Rules Loaded - DATE]`.
-
-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
-- Ground diagnosis in evidence from files and user input
-- This is not therapy. This is debugging. Find the bug, fix it, move.
-
----
-
-## 1. PATTERN CHECK
-
-Before interrogating, check Auto_Learnings.md:
-- Has this resistance pattern appeared before?
-- If recurring (Confidence >= 3): "This isn't new. You've hit this wall before: [Pattern]. Last time, [what happened]. Let's try a different approach."
-- If new: proceed with fresh diagnosis.
-
----
-
-## 2. ISOLATE THE DOMAIN
-
-"Where is the pain? What specific task are you avoiding?"
-Categorize: Sales? Coding? Fitness? Content? Admin?
-
-If user is vague: drill down. "Is it the whole project or one specific action?"
-If user gives a surface answer ("I'm just tired", "I don't feel like it"): reject it. "Tired is a symptom, not a cause. What specifically happens when you sit down to do this task? Where does the resistance hit — before you start, during, or at a specific step?"
-
-**STOP. Wait for user to identify the domain before proceeding to Step 3.**
-
----
-
-## 3. THE BELIEF MAP (Current Self)
-
-"What is the 'Perceived Truth' you are holding right now?"
-(e.g., "If I send this DM, I will look like a spammer.")
-
-Dig deeper — do NOT accept the first answer:
-- "Why do you believe that?"
-- "When did you first start believing this?"
-- "What evidence supports this belief?"
-- "What evidence contradicts it?"
-- If the Perceived Truth is generic ("I'm not good enough", "it won't work"): push to specifics. "Not good enough at WHAT? Compared to WHOM? Based on what evidence?"
-- If the user can't articulate a belief: "You're avoiding it but you can't say why. That usually means the real reason is uncomfortable. Take a guess — what's the worst thing that happens if you do this task?"
-
-**STOP. Wait for user's Perceived Truth before performing the Inversion.**
-
----
-
-## 4. THE INVERSION (Evolving Self)
-
-Apply the Inversion:
-- "What is the stark opposite of that belief?"
-- "How would [Identity from Identity_Prime.md] view this?"
-- "What would the 10-year-from-now version of you say?"
-
-Example:
-- Current: "I'll look like a spammer."
-- Inverted: "I'm holding the cure to their revenue problem. Not telling them is selfish."
-
----
-
-## 5. MICRO-PROOF
-
-"Find one tiny piece of evidence from your past that proves the new belief is true."
-
-If user can't find evidence: help them search.
-- Check Mover_Dossier.md for past wins.
-- Check Daily Notes for similar situations overcome.
-- Check Auto_Learnings for times this pattern was beaten.
-
----
-
-## 6. THE PRESCRIPTION
-
-Based on the diagnosis:
-1. **The Minimum Viable Action:** "What is the smallest possible version of this task? Do THAT. Not the whole thing. Just the first step."
-2. **The Anchor:** "Attach this action to an existing routine. After [routine], do [action]."
-3. **The Accountability:** "Tell me when you've done it."
-
----
-
-## 7. LOG THE RESISTANCE
-
-If this is a new pattern, **propose** logging to Auto_Learnings.md (Engine file — show content, wait for confirmation):
-
-"I'd like to log this resistance pattern to Auto_Learnings.md. Approve?"
-
-```markdown
-## Pattern: [Resistance Name]
-**Domain:** [Business/Vitality/Mind]
-**Status:** ACTIVE
-**Confidence:** 1
-**Last Updated:** [YYYY-MM-DD]
-**Evidence:** [Description of resistance and trigger]
-**Counter-Action:** [The Minimum Viable Action prescribed]
-```
-
-**STOP. Wait for user approval before writing.** After writing, update version/date header.
-
-If existing pattern: increment confidence, update evidence, update Last Updated date.
-
----
-
-## 8. SELF-VERIFICATION (CISC)
-
-Before outputting the prescription, self-check:
-1. Diagnosis grounded in user's stated evidence (not assumed)? (90%+ accuracy)
-2. Inversion rooted in Identity_Prime.md identity, not generic advice?
-3. Minimum Viable Action completable in under 15 minutes?
-4. No banned phrases ("you should," "you need to") in output?
-
-If any section < 90% confident: flag it explicitly before prescribing.
-
----
-
-## 9. ANSWER GATING
-
-Do not suggest handoff until:
-- User has identified the resistance domain (Section 2).
-- User has a Minimum Viable Action they have verbally committed to.
-
-If pending: "You haven't confirmed the action you'll take. 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 this is reboot #3+] - Confidence: [X] - "The pattern may be deeper than one task. Consider `/pivot-strategy`."
-2. [If resistance domain contradicts Strategy.md primary task] - Confidence: [X] - "This task may not be the right one. Alignment check needed."
-3. [If Identity_Prime Anti-Identity matches the resistance] - Confidence: [X] - "This looks like a drift toward your Anti-Identity. Flag for `/analyse-day`."
-
-"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, Daily Note (if loaded)
-Confidence range: [X-Y across outputs]
-
-**Next:** "Now execute. Take the smallest possible action on the thing you were avoiding. Report back."
-
-If the resistance is severe (3+ failed attempts): "Consider whether this task aligns with your Strategy. Sometimes the resistance IS the signal."
-
-Key rules still active:
-- All claims must be grounded in source files or user's own stated evidence
-- Confidence < 3 = ask, don't assert
-- Append-only: never delete from Auto_Learnings.md
+---
+description: Debug psychological resistance through multi-step interrogation. Isolate, map, invert, prove.
+---
+
+# Debug Resistance (V4)
+
+**Trigger:** User says "I'm stuck," "I'm procrastinating," or `/debug-resistance`
+**Role:** Paradigm Surgeon.
+**Task:** Diagnose and dismantle the psychological block preventing execution.
+**Risk Tier:** LOW
+
+---
+
+## 0. PRE-FLIGHT
+
+Global Rules are pre-loaded as CLAUDE.md / GEMINI.md. Output `[Rules Loaded - DATE]`.
+
+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
+- Ground diagnosis in evidence from files and user input
+- This is not therapy. This is debugging. Find the bug, fix it, move.
+
+---
+
+## 1. PATTERN CHECK
+
+Before interrogating, check Auto_Learnings.md:
+- Has this resistance pattern appeared before?
+- If recurring (Confidence >= 3): "This isn't new. You've hit this wall before: [Pattern]. Last time, [what happened]. Let's try a different approach."
+- If new: proceed with fresh diagnosis.
+
+---
+
+## 2. ISOLATE THE DOMAIN
+
+"Where is the pain? What specific task are you avoiding?"
+Categorize: Sales? Coding? Fitness? Content? Admin?
+
+If user is vague: drill down. "Is it the whole project or one specific action?"
+If user gives a surface answer ("I'm just tired", "I don't feel like it"): reject it. "Tired is a symptom, not a cause. What specifically happens when you sit down to do this task? Where does the resistance hit — before you start, during, or at a specific step?"
+
+**STOP. Wait for user to identify the domain before proceeding to Step 3.**
+
+---
+
+## 3. THE BELIEF MAP (Current Self)
+
+"What is the 'Perceived Truth' you are holding right now?"
+(e.g., "If I send this DM, I will look like a spammer.")
+
+Dig deeper — do NOT accept the first answer:
+- "Why do you believe that?"
+- "When did you first start believing this?"
+- "What evidence supports this belief?"
+- "What evidence contradicts it?"
+- If the Perceived Truth is generic ("I'm not good enough", "it won't work"): push to specifics. "Not good enough at WHAT? Compared to WHOM? Based on what evidence?"
+- If the user can't articulate a belief: "You're avoiding it but you can't say why. That usually means the real reason is uncomfortable. Take a guess — what's the worst thing that happens if you do this task?"
+
+**STOP. Wait for user's Perceived Truth before performing the Inversion.**
+
+---
+
+## 4. THE INVERSION (Evolving Self)
+
+Apply the Inversion:
+- "What is the stark opposite of that belief?"
+- "How would [Identity from Identity_Prime.md] view this?"
+- "What would the 10-year-from-now version of you say?"
+
+Example:
+- Current: "I'll look like a spammer."
+- Inverted: "I'm holding the cure to their revenue problem. Not telling them is selfish."
+
+---
+
+## 5. MICRO-PROOF
+
+"Find one tiny piece of evidence from your past that proves the new belief is true."
+
+If user can't find evidence: help them search.
+- Check Mover_Dossier.md for past wins.
+- Check Daily Notes for similar situations overcome.
+- Check Auto_Learnings for times this pattern was beaten.
+
+---
+
+## 6. THE PRESCRIPTION
+
+Based on the diagnosis:
+1. **The Minimum Viable Action:** "What is the smallest possible version of this task? Do THAT. Not the whole thing. Just the first step."
+2. **The Anchor:** "Attach this action to an existing routine. After [routine], do [action]."
+3. **The Accountability:** "Tell me when you've done it."
+
+---
+
+## 7. LOG THE RESISTANCE
+
+If this is a new pattern, **propose** logging to Auto_Learnings.md (Engine file — show content, wait for confirmation):
+
+"I'd like to log this resistance pattern to Auto_Learnings.md. Approve?"
+
+```markdown
+## Pattern: [Resistance Name]
+**Domain:** [Business/Vitality/Mind]
+**Status:** ACTIVE
+**Confidence:** 1
+**Last Updated:** [YYYY-MM-DD]
+**Evidence:** [Description of resistance and trigger]
+**Counter-Action:** [The Minimum Viable Action prescribed]
+```
+
+**STOP. Wait for user approval before writing.** After writing, update version/date header.
+
+If existing pattern: increment confidence, update evidence, update Last Updated date.
+
+---
+
+## 8. SELF-VERIFICATION (CISC)
+
+Before outputting the prescription, self-check:
+1. Diagnosis grounded in user's stated evidence (not assumed)? (90%+ accuracy)
+2. Inversion rooted in Identity_Prime.md identity, not generic advice?
+3. Minimum Viable Action completable in under 15 minutes?
+4. No banned phrases ("you should," "you need to") in output?
+
+If any section < 90% confident: flag it explicitly before prescribing.
+
+---
+
+## 9. ANSWER GATING
+
+Do not suggest handoff until:
+- User has identified the resistance domain (Section 2).
+- User has a Minimum Viable Action they have verbally committed to.
+
+If pending: "You haven't confirmed the action you'll take. 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 this is reboot #3+] - Confidence: [X] - "The pattern may be deeper than one task. Consider `/pivot-strategy`."
+2. [If resistance domain contradicts Strategy.md primary task] - Confidence: [X] - "This task may not be the right one. Alignment check needed."
+3. [If Identity_Prime Anti-Identity matches the resistance] - Confidence: [X] - "This looks like a drift toward your Anti-Identity. Flag for `/analyse-day`."
+
+"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, Daily Note (if loaded)
+Confidence range: [X-Y across outputs]
+
+**Next:** "Now execute. Take the smallest possible action on the thing you were avoiding. Report back."
+
+If the resistance is severe (3+ failed attempts): "Consider whether this task aligns with your Strategy. Sometimes the resistance IS the signal."
+
+Key rules still active:
+- All claims must be grounded in source files or user's own stated evidence
+- Confidence < 3 = ask, don't assert
+- Append-only: never delete from Auto_Learnings.md