monomind 2.7.12 → 2.7.14

package/packages/@monomind/cli/.claude/skills/mastermind-marketing/references/copywriting-frameworks.md

@@ -1,181 +0,0 @@
-# Copywriting Frameworks Reference
-
-Headline formulas, page structure templates, CTA patterns, and writing principles for marketing pages. Use when writing or reviewing landing pages, homepages, pricing pages, feature pages, or any conversion-focused surface.
-
----
-
-## Writing Principles
-
-### The Hierarchy
-1. **Clarity over cleverness** — If you have to choose, choose clear
-2. **Benefits over features** — Features: what it does. Benefits: what that means for the customer
-3. **Specificity over vagueness** — "Cut weekly reporting from 4 hours to 15 minutes" beats "Save time on your workflow"
-4. **Customer language over company language** — Mirror words from reviews, interviews, support tickets
-5. **Active over passive** — "We generate reports" not "Reports are generated"
-6. **Confident over qualified** — Remove "almost", "very", "really", "quite"
-7. **One idea per section** — Each section advances one argument; build a logical flow down the page
-
-### Quick Quality Check
-- Jargon that could confuse an outsider?
-- Sentences trying to do too much?
-- Passive voice constructions?
-- Exclamation points? (remove them)
-- Marketing buzzwords without substance? (streamline, optimize, innovative, leverage)
-- "We/our" dominating over "you/your"?
-
----
-
-## Headline Formulas
-
-### Outcome-Focused
-- `{Achieve outcome} without {pain point}` → "Understand how users experience your site without drowning in numbers"
-- `{Achieve outcome} by {how product makes it possible}` → "Generate more leads by seeing which companies visit your site"
-- `Turn {input} into {outcome}` → "Turn your hard-earned sales into repeat customers"
-- `[Achieve outcome] in [timeframe]` → "Get your tax refund in 10 days"
-
-### Problem-Focused
-- `Never {unpleasant event} again` → "Never miss a sales opportunity again"
-- `{Question highlighting the main pain point}` → "Hate returning stuff to Amazon?"
-- `Stop [pain]. Start [pleasure].` → "Stop chasing invoices. Start getting paid on time."
-
-### Audience-Focused
-- `{Key feature} for {target audience}` → "Advanced analytics for Shopify stores"
-- `{Key feature} for {target audience} to {outcome}` → "An online whiteboard for teams to ideate together"
-- `You don't have to {skill} to {achieve outcome}` → "You don't have to be an SEO pro to rank higher"
-
-### Differentiation-Focused
-- `The {opposite of usual} way to {achieve outcome}` → "The easiest way to turn your passion into income"
-- `The [category] that [key differentiator]` → "The CRM that updates itself"
-
-### Proof-Focused
-- `[Number] [people] use [product] to [outcome]` → "50,000 marketers use Drip to send better emails"
-- `{Key benefit of your product}` → "Sound clear in online meetings"
-
-### Additional Formulas
-- `The simple way to {outcome}` → "The simple way to track your time"
-- `Finally, {category} that {benefit}` → "Finally, accounting software that doesn't suck"
-- `{Outcome} without {common pain}` → "Build your website without writing code"
-- `What if you could {desirable outcome}?` → "What if you could close deals 30% faster?"
-- `Everything you need to {outcome}` → "Everything you need to launch your course"
-- `The {adjective} {category} built for {audience}` → "The lightweight CRM built for startups"
-- `{Action verb} your {thing} like {admirable example}` → "Market your SaaS like a Fortune 500"
-
----
-
-## Page Structure
-
-### Above the Fold
-**Headline** — Single most important message. Core value prop. Specific > generic.
-**Subheadline** — Expands headline. Adds specificity. 1-2 sentences max.
-**Primary CTA** — Action-oriented. Communicate what they get: "Start Free Trial" > "Sign Up"
-**Supporting element** — Social proof count, trust badge, or hero image
-
-### Core Section Types
-| Section | Purpose | Notes |
-|---|---|---|
-| Social Proof | Build credibility | Logos near CTA, stats, specific testimonials |
-| Problem / Pain | Show you understand | Mirror customer language, not company framing |
-| Solution / Benefits | Connect to outcomes | 3-5 key benefits, not feature list |
-| How It Works | Reduce complexity | 3-4 numbered steps |
-| Objection Handling | Remove hesitation | FAQ, comparison, guarantee |
-| Final CTA | Recap + action | Restate value, repeat CTA, risk reversal |
-
-### Page Templates
-
-**Compact Landing Page** (single offer, cold traffic):
-Above fold → Social proof strip → Problem → Solution/benefits → How it works → Testimonials → CTA
-
-**Feature-Heavy Product Page**:
-Above fold → Social proof → Core value → Feature 1 (problem → feature → benefit) → Feature 2 → Feature 3 → Testimonials → FAQ → CTA
-
-**Enterprise / B2B Landing Page**:
-Above fold (value + credibility) → Problem/stakes → Solution overview → Proof (logos + case study) → How it works → Security/compliance → Testimonials → CTA + Demo request
-
-**Product Launch Page**:
-Above fold (bold announcement) → Why now → What it is → Key capabilities → Social proof from beta → Pricing → FAQ → CTA
-
----
-
-## CTA Copy Guidelines
-
-### Weak CTAs (avoid)
-Submit, Sign Up, Learn More, Click Here, Get Started, Download
-
-### Strong CTAs (use)
-- "Start Free Trial"
-- "Get [Specific Thing]" → "Get the Complete Checklist"
-- "See [Product] in Action"
-- "Create Your First [Thing]"
-- "[Action] for Free"
-
-### Formula
-`[Action Verb] + [What They Get] + [Qualifier if needed]`
-- "Start My Free Trial"
-- "See Pricing for My Team"
-- "Download the 2025 Report"
-
----
-
-## Page-Specific Copy Guidance
-
-### Homepage
-- Serve multiple audiences without being generic
-- Lead with broadest value proposition
-- Provide clear paths for different visitor intents ("I'm a designer" / "I'm an engineer")
-- Don't try to close — guide toward the right next page or CTA
-
-### Landing Page
-- Single message, single CTA — remove navigation if possible
-- Match headline exactly to the ad or email that sent traffic here
-- Complete the argument on one page; don't assume they'll come back
-
-### Pricing Page
-- Help visitors choose the right plan — answer "which is right for me?"
-- Make recommended plan obvious (badge, highlight, preselected)
-- Address the top 3-4 objections in an FAQ
-- Annual toggle with savings stated in dollars and percentage
-
-### Feature Page
-- Connect: feature → benefit → outcome (not feature → feature → feature)
-- Show use cases and examples, not just capabilities
-- Clear path to try or buy at the bottom
-
-### About Page
-- Tell the story of why this exists (founding insight or problem)
-- Connect mission to customer benefit
-- Still include a CTA — this is often a high-intent page
-
----
-
-## Writing for Trust
-
-### Social Proof Placement
-- Customer logos: above the fold (strip) and near primary CTA
-- Testimonials: specific quote + name + title + company + photo; near the claim they validate
-- Numbers: exact figures beat vague ("10,247 teams" not "thousands of teams")
-- Reviews: third-party star ratings add credibility you can't self-claim
-
-### Objection Handling
-Name the objection directly, then resolve it:
-- "What if it's not right for us?" → Money-back guarantee / free trial
-- "How long does setup take?" → "Live in 10 minutes, no IT required"
-- "Is my data secure?" → SOC 2 Type II, encryption at rest, specific certifications
-
-### Risk Reversals
-- "Free 14-day trial, no credit card required"
-- "Cancel anytime — no questions asked"
-- "30-day money-back guarantee"
-- "Free migration assistance"
-
----
-
-## Copy Anti-Patterns
-
-Never:
-- Start a CTA with "Click here" or "Learn more" — be specific about the outcome
-- Use passive voice in problem statements ("An error was encountered")
-- Hedge: "This might help", "You may want to", "Perhaps consider"
-- Restate the heading in the first sentence of body copy
-- Write "Successfully saved" when "Saved" says the same in half the words
-- Use em dashes — use commas, colons, or periods instead
-- Open with "We are pleased to announce..." or "We are excited to share..."

package/packages/@monomind/cli/.claude/skills/mastermind-marketing/references/persuasion-psychology.md

@@ -1,158 +0,0 @@
-# Persuasion Psychology Reference
-
-Mental models, cognitive biases, and behavioral frameworks for marketing. Apply these when writing copy, designing campaigns, structuring pricing, or briefing agents on how to frame their output.
-
----
-
-## Quick Reference: Challenge → Models
-
-| Challenge | Apply These |
-|---|---|
-| Low conversions | Hick's Law, Activation Energy, BJ Fogg, friction reduction |
-| Price objections | Anchoring, Framing, Mental Accounting, Loss Aversion |
-| Building trust | Authority, Social Proof, Reciprocity, Mere Exposure |
-| Creating urgency | Scarcity, Loss Aversion, Zeigarnik Effect |
-| Retention/churn | Endowment Effect, Switching Costs, Status-Quo Bias |
-| Growth stalling | Theory of Constraints, Pareto, Feedback Loops |
-| Decision paralysis | Paradox of Choice, Default Effect, Decoy Effect |
-| Onboarding | Goal-Gradient, IKEA Effect, Commitment & Consistency |
-| Cold outreach | Reciprocity, Authority, Liking/Similarity, Mere Exposure |
-
----
-
-## Cognitive Biases
-
-### Anchoring Effect
-The first number seen heavily influences subsequent judgments. Show the higher price first (enterprise tier, competitor price, original price) to anchor expectations before revealing your price.
-
-### Loss Aversion
-Losses feel roughly twice as painful as equivalent gains. Frame in terms of what they'll lose by not acting. "Don't miss out" outperforms "You could gain." "Stop losing $X/week" beats "Save $X/week."
-
-### Social Proof / Bandwagon Effect
-People follow what others are doing. Popularity signals quality and safety. Show customer counts, testimonials with photos, company logos, review scores, and "trending" indicators near CTAs.
-
-### Scarcity / Urgency
-Limited availability increases perceived value. Limited-time offers, low-stock warnings, and exclusive access create urgency. Only use when genuine — fake scarcity destroys trust permanently.
-
-### Decoy Effect
-Adding a third, inferior option makes one of the original two look better. A pricing tier that's clearly worse value makes your preferred tier look like the obvious choice.
-
-### Framing Effect
-Same facts, different frames. "90% success rate" vs. "10% failure rate" are identical but feel different. Frame positively. "Keep your savings" beats "Avoid losing money."
-
-### Default Effect
-People accept pre-selected options. Defaults are powerful. Pre-select the plan you want customers to choose. The recommended tier should be visually pre-selected.
-
-### Paradox of Choice
-Too many options overwhelm and paralyze. Fewer choices often lead to more decisions. Three pricing tiers beat seven. One clear CTA beats three. Recommend a single "best for most" option.
-
-### Goal-Gradient Effect
-People accelerate effort as they approach a goal. Show progress bars, completion percentages, and "almost there" messaging to drive completion in onboarding and signup flows.
-
-### Endowment Effect
-People value things more once they own them. Free trials, samples, and freemium models let customers "own" the product before committing, making them reluctant to give it up.
-
-### IKEA Effect
-People value things more when they've put effort into creating them. Let customers customize, configure, or build something during onboarding. Their investment increases perceived value.
-
-### Zero-Price Effect
-"Free" is psychologically different from low-priced. The jump from $1 to $0 is disproportionately powerful. Free tiers, free shipping, and free trials have outsized appeal.
-
-### Status-Quo Bias
-People prefer the current state. Change feels risky. Reduce friction to switch: "Import your data in one click." Make the transition feel safe and easy, not effortful.
-
-### Zeigarnik Effect
-Unfinished tasks occupy the mind. Open loops create tension. "You're 80% done" creates pull to finish. Abandoned carts, incomplete profiles, and progress indicators leverage this.
-
-### Mere Exposure Effect
-Familiarity breeds liking. Consistent brand presence builds preference over time. Repetition across channels creates comfort and trust — even without explicit recall.
-
-### Confirmation Bias
-People seek information confirming existing beliefs. Understand what your audience already believes and align messaging accordingly. Fighting beliefs head-on rarely works.
-
-### Hyperbolic Discounting / Present Bias
-People strongly prefer immediate rewards. Emphasize immediate benefits ("Start saving time today") over future ones ("You'll see ROI in 6 months").
-
----
-
-## Persuasion Principles
-
-### Reciprocity
-People feel obligated to return favors. Give first: free content, free tools, generous free tiers create reciprocal obligation. Give value before asking for anything.
-
-### Commitment & Consistency
-Once people commit, they want to stay consistent. Get small commitments first (email signup, free trial). People who've taken one step are more likely to take the next.
-
-### Authority Bias
-People defer to experts. Feature expert endorsements, certifications, "as seen in" logos, and thought leadership content. Credentials reduce perceived risk.
-
-### Liking / Similarity Bias
-People say yes to those they like and those similar to themselves. "Built by marketers for marketers" signals similarity. Use relatable spokespeople and shared-values positioning.
-
-### Scarcity (see Cognitive Biases above)
-
-### Unity Principle
-Shared identity drives influence. Position your brand as part of the customer's tribe. Use insider language and shared values.
-
----
-
-## Pricing Psychology
-
-### Charm Pricing / Left-Digit Effect
-Prices ending in 9 seem significantly lower than the next round number. $99 feels much cheaper than $100. Use for value-focused products.
-
-### Rounded-Price (Fluency) Effect
-Round numbers feel premium. $100 signals quality; $99 signals value. Use round prices for premium products, charm prices for value products.
-
-### Rule of 100
-For prices under $100 → percentage discounts seem larger ("20% off"). For prices over $100 → absolute discounts seem larger ("$50 off").
-
-### Mental Accounting
-Same price framed differently changes perception. "$1/day" feels cheaper than "$30/month." "Less than your morning coffee" reframes the expense.
-
----
-
-## Behavioral Models
-
-### BJ Fogg Behavior Model
-Behavior = Motivation × Ability × Prompt. All three must be present for action. High motivation but hard to do = won't happen. Easy to do but no prompt = won't happen. Design for all three in every CTA.
-
-### EAST Framework
-Make desired behaviors: **Easy** (reduce friction), **Attractive** (appealing visually and verbally), **Social** (show others doing it), **Timely** (ask at the right moment in the journey).
-
-### Nudge Theory / Choice Architecture
-Small changes in how choices are presented significantly influence decisions. Default selections, strategic ordering, and friction reduction guide behavior without restricting choice.
-
-### Activation Energy
-The initial energy required to start. High activation energy prevents action even if the overall task is easy. Pre-fill forms, offer templates, show quick wins. Make the first step trivially easy.
-
-### Feedback Loops
-Output becomes input. Build virtuous cycles: more users → more content → better SEO → more users. Identify and strengthen positive feedback loops in your marketing system.
-
-### Flywheel Effect
-Sustained effort creates self-sustaining momentum. Content → traffic → leads → customers → case studies → more content. Each element powers the next.
-
-### Theory of Constraints
-Every system has one bottleneck. Fix the constraint before optimizing elsewhere. If funnel converts well but traffic is low, more CRO won't help. Fix the bottleneck first.
-
----
-
-## Mental Models for Strategy
-
-### Jobs to Be Done
-People don't buy products — they hire them to get a job done. A drill buyer wants a hole. Frame around the job (outcome), not the tool (feature).
-
-### First Principles
-Break problems down to basic truths. Ask "why" repeatedly to find root causes. Don't assume you need content marketing because competitors do — ask what problem it solves.
-
-### Inversion
-Ask "What would guarantee failure?" then systematically prevent those things. List everything that would make your campaign fail before building it.
-
-### Pareto Principle (80/20)
-80% of results come from 20% of efforts. Find the 20% of channels, customers, or content driving 80% of results. Cut or reduce the rest.
-
-### Second-Order Thinking
-Consider effects of effects. A flash sale boosts revenue (first order) but trains customers to wait for discounts (second order). Think two moves ahead.
-
-### Barbell Strategy
-Put 80% of budget into proven channels, 20% into experimental bets. Avoid moderate-risk, moderate-reward middle ground.

package/packages/@monomind/cli/.claude/skills/mastermind-memory/SKILL.md

@@ -1,321 +0,0 @@
----
-name: mastermind-memory
-description: Mastermind memory — org-scoped persistent memory using PARA method (Projects, Areas, Resources, Archives). Ingest facts, recall context, maintain knowledge graph, run weekly synthesis. Reads from .monomind/orgs/<org>-memory/ directory. Port of Paperclip's para-memory-files skill for org-level context.
-type: domain-skill
-default_mode: auto
----
-
-# Mastermind Memory
-
-This skill is invoked by `mastermind:memory` or directly via `/mastermind:memory`.
-
----
-
-## Inputs
-
-- `brain_context`: BRAIN CONTEXT block (injected by command, or loaded below if standalone)
-- `org_name`: org whose memory to operate on (required)
-- `action`: ingest | recall | query | update | forget | synthesize | decay | list
-- `topic`: topic or entity name (required for ingest/recall/update/forget)
-- `layer`: knowledge | daily | tacit (default: knowledge)
-- `category`: projects | areas | resources | archives (for layer=knowledge; default: resources)
-- `content`: fact or note body (required for ingest/update)
-- `caller`: command | master
-
----
-
-## Memory Architecture (PARA)
-
-Three layers, mirrored to `.monomind/orgs/<org_name>-memory/`:
-
-```
-.monomind/orgs/<org>-memory/
-  knowledge/              ← Layer 1: PARA knowledge graph
-    projects/<topic>/
-      summary.md
-      items.yaml
-    areas/<topic>/
-      summary.md
-      items.yaml
-    resources/<topic>/
-      summary.md
-      items.yaml
-    archives/<topic>/
-      summary.md
-      items.yaml
-    index.md
-  daily/                  ← Layer 2: Raw timeline (YYYY-MM-DD.md)
-  tacit.md                ← Layer 3: Org operating patterns
-```
-
-**PARA rules:**
-- **projects** — active work with a goal/deadline; archive when complete
-- **areas** — ongoing responsibilities, no end date
-- **resources** — reference material, topics of interest
-- **archives** — inactive items from any category
-
----
-
-## Step 0 — Brain Load (standalone only)
-
-If `caller` is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: `ops`.
-
----
-
-## Step 1 — Resolve Memory Root
-
-```bash
-memRoot=".monomind/orgs/${org_name}-memory"
-mkdir -p "$memRoot/knowledge/projects" "$memRoot/knowledge/areas" \
-         "$memRoot/knowledge/resources" "$memRoot/knowledge/archives" \
-         "$memRoot/daily"
-```
-
----
-
-## Step 2 — Execute Action
-
-### ingest (default for new facts)
-
-Store a durable fact in Layer 1 (knowledge graph) or Layer 2 (daily note).
-
-```bash
-ts=$(date -u +%Y-%m-%dT%H:%M:%SZ)
-day=$(date -u +%Y-%m-%d)
-layer="${layer:-knowledge}"
-category="${category:-resources}"
-topicSlug=$(echo "${topic:-general}" | tr '[:upper:]' '[:lower:]' | tr ' ' '-' | tr -cd 'a-z0-9-')
-
-if [ "$layer" = "daily" ]; then
-  dailyFile="$memRoot/daily/${day}.md"
-  [ ! -f "$dailyFile" ] && echo "# Daily Notes — ${day}" > "$dailyFile"
-  echo "" >> "$dailyFile"
-  echo "## [${ts}] ${topic:-note}" >> "$dailyFile"
-  echo "${content}" >> "$dailyFile"
-  echo "  [daily] Appended to $dailyFile"
-elif [ "$layer" = "tacit" ]; then
-  [ ! -f "$memRoot/tacit.md" ] && echo "# Org Operating Patterns — ${org_name}" > "$memRoot/tacit.md"
-  echo "" >> "$memRoot/tacit.md"
-  echo "## ${topic}" >> "$memRoot/tacit.md"
-  echo "${content}" >> "$memRoot/tacit.md"
-  echo "  [tacit] Pattern saved."
-else
-  # Layer 1: knowledge graph
-  entityDir="$memRoot/knowledge/${category}/${topicSlug}"
-  mkdir -p "$entityDir"
-  factId="fact-$(python3 -c 'import time; print(int(time.time()*1000))')"
-  python3 - "$entityDir/items.yaml" "$factId" "${topic}" "${content}" "$ts" <<'PYEOF'
-import sys, yaml, os
-path, fid, topic, body, ts = sys.argv[1:]
-facts = []
-if os.path.exists(path):
-    try:
-        with open(path) as f:
-            loaded = yaml.safe_load(f)
-            if isinstance(loaded, list): facts = loaded
-    except: pass
-facts.append({"id": fid, "topic": topic, "body": body, "createdAt": ts, "status": "active"})
-with open(path, "w") as f:
-    yaml.dump(facts, f, default_flow_style=False, allow_unicode=True)
-print(f"  Fact saved: {fid} → {path}")
-PYEOF
-fi
-```
-
-### recall / query
-
-Search org memory across all layers for a topic or keyword.
-
-```bash
-q="${topic:-${content}}"
-echo "MEMORY RECALL — ${org_name}"
-echo "Query: $q"
-echo "────────────────────────────────────────────────────────"
-
-python3 - "$memRoot" "$q" <<'PYEOF'
-import os, sys, yaml, re
-root, query = sys.argv[1], sys.argv[2].lower()
-results = []
-
-# Layer 1: scan items.yaml files
-kg = os.path.join(root, "knowledge")
-for cat in ["projects","areas","resources","archives"]:
-    cpath = os.path.join(kg, cat)
-    if not os.path.isdir(cpath): continue
-    for topic in os.listdir(cpath):
-        ypath = os.path.join(cpath, topic, "items.yaml")
-        if not os.path.exists(ypath): continue
-        try:
-            facts = yaml.safe_load(open(ypath)) or []
-            for f in facts:
-                if f.get("status") == "superseded": continue
-                body = str(f.get("body","")).lower()
-                ftopic = str(f.get("topic","")).lower()
-                if query in body or query in ftopic or query in topic.lower():
-                    results.append(("knowledge/"+cat+"/"+topic, f.get("createdAt","?")[:10], f.get("body","")[:120]))
-        except: pass
-
-# Layer 2: daily notes
-daily_dir = os.path.join(root, "daily")
-if os.path.isdir(daily_dir):
-    for fname in sorted(os.listdir(daily_dir), reverse=True)[:30]:
-        try:
-            text = open(os.path.join(daily_dir, fname)).read().lower()
-            if query in text:
-                results.append(("daily/"+fname, fname[:10], "(match in daily notes)"))
-        except: pass
-
-# Layer 3: tacit
-tacit = os.path.join(root, "tacit.md")
-if os.path.exists(tacit):
-    text = open(tacit).read().lower()
-    if query in text:
-        results.append(("tacit.md", "", "(match in org patterns)"))
-
-if not results:
-    print("  No matches found.")
-else:
-    print(f"  {len(results)} result(s):")
-    for path, date, body in results[:20]:
-        print(f"\n  [{date}] {path}")
-        print(f"    {body[:100]}{'...' if len(body)>100 else ''}")
-PYEOF
-```
-
-### list
-
-List all entities in the knowledge graph.
-
-```bash
-echo "KNOWLEDGE GRAPH — ${org_name}"
-echo "────────────────────────────────────────────────────────"
-
-python3 - "$memRoot/knowledge" <<'PYEOF'
-import os, sys, yaml
-kg = sys.argv[1]
-total = 0
-for cat in ["projects","areas","resources","archives"]:
-    cpath = os.path.join(kg, cat)
-    if not os.path.isdir(cpath): continue
-    topics = [d for d in os.listdir(cpath) if os.path.isdir(os.path.join(cpath,d))]
-    if not topics: continue
-    print(f"\n  {cat.upper()} ({len(topics)})")
-    for t in sorted(topics):
-        ypath = os.path.join(cpath, t, "items.yaml")
-        count = 0
-        try:
-            facts = yaml.safe_load(open(ypath)) or []
-            count = len([f for f in facts if f.get("status") != "superseded"])
-        except: pass
-        print(f"    · {t}  ({count} facts)")
-    total += len(topics)
-print(f"\n  Total entities: {total}")
-PYEOF
-```
-
-### forget
-
-Mark a fact as superseded (never delete — supersede).
-
-```bash
-topicSlug=$(echo "${topic}" | tr '[:upper:]' '[:lower:]' | tr ' ' '-' | tr -cd 'a-z0-9-')
-ts=$(date -u +%Y-%m-%dT%H:%M:%SZ)
-category="${category:-resources}"
-entityDir="$memRoot/knowledge/${category}/${topicSlug}"
-ypath="$entityDir/items.yaml"
-
-python3 - "$ypath" "$ts" "${content:-forgot}" <<'PYEOF'
-import sys, yaml, os
-path, ts, reason = sys.argv[1], sys.argv[2], sys.argv[3]
-if not os.path.exists(path):
-    print("  No facts found for this entity.")
-    sys.exit(0)
-facts = yaml.safe_load(open(path)) or []
-active = [f for f in facts if f.get("status") == "active"]
-for f in active:
-    f["status"] = "superseded"
-    f["supersededAt"] = ts
-    f["supersededReason"] = reason
-with open(path, "w") as out:
-    yaml.dump(facts, out, default_flow_style=False, allow_unicode=True)
-print(f"  {len(active)} fact(s) superseded in {path}")
-PYEOF
-```
-
-### synthesize
-
-Rebuild summary.md for an entity from its active facts.
-
-```bash
-topicSlug=$(echo "${topic}" | tr '[:upper:]' '[:lower:]' | tr ' ' '-' | tr -cd 'a-z0-9-')
-category="${category:-resources}"
-entityDir="$memRoot/knowledge/${category}/${topicSlug}"
-ypath="$entityDir/items.yaml"
-[ ! -f "$ypath" ] && { echo "  No facts found for '${topic}'."; exit 0; }
-
-python3 - "$ypath" "$entityDir/summary.md" "${topic}" <<'PYEOF'
-import sys, yaml
-ypath, sumpath, topic = sys.argv[1], sys.argv[2], sys.argv[3]
-facts = [f for f in (yaml.safe_load(open(ypath)) or []) if f.get("status") == "active"]
-lines = [f"# {topic}", "", f"{len(facts)} active fact(s):", ""]
-for f in facts:
-    date = str(f.get("createdAt","?"))[:10]
-    lines.append(f"- [{date}] {f.get('body','')}")
-open(sumpath, "w").write("\n".join(lines) + "\n")
-print(f"  Summary rebuilt: {sumpath}")
-PYEOF
-```
-
-### decay
-
-Archive entities with no facts updated in the last 90 days.
-
-```bash
-ts=$(date -u +%Y-%m-%dT%H:%M:%SZ)
-
-python3 - "$memRoot/knowledge" "$ts" <<'PYEOF'
-import os, sys, yaml, shutil
-from datetime import datetime, timedelta
-kg, ts = sys.argv[1], sys.argv[2]
-cutoff = datetime.utcnow() - timedelta(days=90)
-archived = 0
-for cat in ["projects","areas","resources"]:
-    cpath = os.path.join(kg, cat)
-    if not os.path.isdir(cpath): continue
-    for topic in os.listdir(cpath):
-        ypath = os.path.join(cpath, topic, "items.yaml")
-        if not os.path.exists(ypath): continue
-        try:
-            facts = yaml.safe_load(open(ypath)) or []
-            active = [f for f in facts if f.get("status") == "active"]
-            if not active: continue
-            last = max(f.get("createdAt","")[:19] for f in active)
-            dt = datetime.fromisoformat(last)
-            if dt < cutoff:
-                dst = os.path.join(kg, "archives", topic)
-                shutil.move(os.path.join(cpath, topic), dst)
-                archived += 1
-                print(f"  Archived: {cat}/{topic} (last active: {last[:10]})")
-        except: pass
-print(f"\n  Decay complete: {archived} entity/entities moved to archives.")
-PYEOF
-```
-
----
-
-## Step 3 — Return Output
-
-```yaml
-domain: ops
-status: complete
-action: <action>
-org_name: <org_name>
-layer: <layer>
-topic: <topic>
-```
-
----
-
-## Step 4 — Brain Write (standalone only)
-
-If `caller` is not "command", follow mastermind-protocol/SKILL.md Brain Write Procedure for domain `ops`.