docs: remove references to unimplemented AlgorithmTab.hook.ts

.gitignore

@@ -1,68 +1,60 @@
-# macOS
-.DS_Store
-.AppleDouble
-.LSOverride
-Icon
-._*
-.Spotlight-V100
-.Trashes
-Library
 
+# API keys and secrets
+# Build outputs
+# Cache
 # Environment files
-.env
-.env.local
-.env.*.local
+# IDE
+# Logs
+# Node/Bun
+# PAI Update System (sideloading)
+# Personal/Private data
+# Temporary files
+# macOS
+*.cache
+*.cer
+*.cert
+*.crt
 *.env
-
-# API keys and secrets
-*.pem
 *.key
-*.cert
+*.log
 *.p12
+*.pem
 *.pfx
+*.swo
+*.swp
+*.tmp
 *_rsa
 *_rsa.pub
-*.crt
-*.cer
-
-# Logs
-*.log
-logs/
-Library/Logs/
-
-# Node/Bun
-node_modules/
+*~
+.AppleDouble
+.DS_Store
+.LSOverride
+.Spotlight-V100
+.Trashes
+._*
+.cache/
+.claude/.pai-sync-history
+.claude/pai_backups/
+.claude/pai_updates/
+.env
+.env.*.local
+.env.local
+.idea/
 .npm
-.yarn
 .pnp.*
-
-# IDE
 .vscode/
-.idea/
-*.swp
-*.swo
-*~
-
-# Temporary files
-tmp/
-temp/
-*.tmp
-
-# Build outputs
-dist/
+.yarn
+Icon
+Library
+Library/Logs/
+Private-Packs/
 build/
+credentials/
+dist/
+logs/
+node_modules/
 out/
-
-# Cache
-.cache/
-*.cache
-
-# Personal/Private data
 private/
 secrets/
-credentials/
-
-# PAI Update System (sideloading)
-.claude/pai_updates/
-.claude/pai_backups/
-.claude/.pai-sync-history
+temp/
+tmp/

.pai-release

@@ -0,0 +1 @@
+v4.0.0

HYBRID-WORKFLOW.md

@@ -0,0 +1,176 @@
+# PAI Hybrid Development Workflow
+
+This documents the hybrid workflow for PAI development: iterate fast in `~/.claude`, formalize to Packs when ready.
+
+## The Two Locations
+
+**Installation Directory (`~/.claude/`):**
+- Where PAI actually runs
+- Fast iteration and testing
+- Changes take effect immediately
+- Not version controlled directly
+
+**Repository Directory (`~/PAI/Packs/`):**
+- Source code in version control
+- Proper Pack structure
+- Syncs to `~/.claude` via `update-pai.sh`
+
+## Hybrid Workflow
+
+### Phase 1: Development (Fast Iteration)
+
+Work directly in `~/.claude` for quick iteration:
+
+```bash
+# Edit files directly in installation
+vim ~/.claude/hooks/SomeHook.ts
+vim ~/.claude/skills/SomeSkill/SKILL.md
+
+# Test immediately - changes are live
+claude
+
+# Iterate quickly until stable
+```
+
+### Phase 2: Formalization (Version Control)
+
+Once stable, copy to Pack structure:
+
+```bash
+# 1. Find which Pack owns the file
+find ~/PAI/Packs -name "SomeHook.ts"
+
+# 2. Copy from installation to Pack
+cp ~/.claude/hooks/SomeHook.ts ~/PAI/Packs/pai-hook-system/src/hooks/
+
+# 3. Stage and commit
+cd ~/PAI
+git add Packs/
+git commit -m "feat: Description of changes"
+
+# 4. Push to your fork
+git push origin main
+```
+
+### Phase 3: Deployment (Optional)
+
+Deploy Pack changes back to `~/.claude`:
+
+```bash
+cd ~/PAI
+./update-pai.sh
+```
+
+This re-deploys from Packs to `~/.claude`. Useful if:
+- You want to test the Pack deployment process
+- You've updated from upstream
+- You're setting up on a new machine
+
+## File Mapping Reference
+
+Common file locations:
+
+| Installation (`~/.claude`) | Pack Source (`~/PAI/Packs`) |
+|---------------------------|----------------------------|
+| `hooks/LoadContext.hook.ts` | `pai-hook-system/src/hooks/LoadContext.hook.ts` |
+| `skills/CORE/SKILL.md` | `pai-core-install/src/skills/CORE/SKILL.md` |
+| `vault-examples/` | `pai-core-install/src/vault-examples/` |
+
+## Finding Which Pack Owns a File
+
+```bash
+# Search by filename
+find ~/PAI/Packs -name "LoadContext.hook.ts"
+
+# Search by path component
+find ~/PAI/Packs -path "*/hooks/*" -name "*.ts"
+find ~/PAI/Packs -path "*/skills/CORE/*"
+```
+
+## Quick Reference Commands
+
+**Sync installation → Pack:**
+```bash
+cp ~/.claude/path/to/file.ts ~/PAI/Packs/pack-name/src/path/to/file.ts
+```
+
+**Commit to git:**
+```bash
+cd ~/PAI
+git add Packs/
+git commit -m "feat: Your change description"
+git push origin main
+```
+
+**Deploy Pack → installation:**
+```bash
+cd ~/PAI
+./update-pai.sh
+```
+
+## Best Practices
+
+1. **Develop in `~/.claude`** - Fast, immediate feedback
+2. **Test thoroughly** - Make sure it works before formalizing
+3. **Copy to Packs when stable** - Version control the working solution
+4. **Commit with good messages** - Describe what and why
+5. **Push regularly** - Keep your fork up to date
+
+## Example: Vault Loading Feature
+
+This feature followed the hybrid workflow:
+
+### Development Phase:
+- Modified `~/.claude/hooks/LoadContext.hook.ts` directly
+- Added vault section to `~/.claude/skills/CORE/SKILL.md`
+- Created `~/.claude/vault-examples/`
+- Tested with sample vaults
+- Iterated on implementation
+
+### Formalization Phase:
+- Copied LoadContext.hook.ts to `Packs/pai-hook-system/src/hooks/`
+- Copied SKILL.md to `Packs/pai-core-install/src/skills/CORE/`
+- Copied vault-examples/ to `Packs/pai-core-install/src/`
+- Committed: "feat: Add per-vault context loading"
+- Pushed to fork
+
+### Result:
+- Working feature in `~/.claude`
+- Version controlled in `~/PAI`
+- Ready to contribute upstream if desired
+- Can be deployed to new machines via `update-pai.sh`
+
+## When to Skip Formalization
+
+Some changes should stay in `~/.claude` only:
+
+- **Personal customizations** - Specific to your workflow
+- **Experimental features** - Still iterating, not stable
+- **Machine-specific config** - Paths, credentials, etc.
+- **USER/ tier content** - Your personal data, not infrastructure
+
+For these, `.gitignore` them or keep them out of Packs entirely.
+
+## Upstream Contribution
+
+To contribute to danielmiessler/PAI:
+
+1. Ensure feature is in Pack structure (formalized)
+2. Test with `update-pai.sh` deployment
+3. Document in Pack's README.md
+4. Create pull request to upstream:
+   ```bash
+   cd ~/PAI
+   git push origin feature-branch
+   # Then create PR on GitHub: HyggeHacker/PAI → danielmiessler/PAI
+   ```
+
+## Summary
+
+**Hybrid workflow = Best of both worlds:**
+- ✅ Fast iteration in `~/.claude`
+- ✅ Version control in `~/PAI`
+- ✅ Proper architecture when ready
+- ✅ Can contribute upstream
+
+**The key:** Don't let perfect be the enemy of good. Iterate fast, formalize when stable.

Packs/pai-core-install/src/skills/CORE/Components/00-frontmatter.md

@@ -0,0 +1,9 @@
+<!--
+  🔨 GENERATED FILE - Do not edit directly
+  Edit:   ~/.claude/skills/CORE/Components/
+  Build:  bun ~/.claude/skills/CORE/Tools/CreateDynamicCore.ts
+-->
+---
+name: CORE
+description: Personal AI Infrastructure core. The authoritative reference for how PAI works.
+---

Packs/pai-core-install/src/skills/CORE/Components/10-pai-intro.md

@@ -0,0 +1,4 @@
+
+# Intro to PAI
+
+The PAI system is designed to magnify human capabilities. It is a general problem-solving system that uses the PAI Algorithm.

Packs/pai-core-install/src/skills/CORE/Components/15-format-mode-selection.md

@@ -0,0 +1,25 @@
+
+# RESPONSE DEPTH SELECTION (Read First)
+
+**Nothing escapes the Algorithm. The only variable is depth.**
+
+The FormatReminder hook uses AI inference to classify depth. Its classification is **authoritative** — do not override it.
+
+| Depth | When | Format |
+|-------|------|--------|
+| **FULL** | Any non-trivial work: problem-solving, implementation, design, analysis, thinking | 7 phases with ISC Tasks |
+| **ITERATION** | Continuing/adjusting existing work in progress | Condensed: What changed + Verify |
+| **MINIMAL** | Pure social with zero task content: greetings, ratings (1-10), acknowledgments only | Header + Summary + Voice |
+
+**ITERATION Format** (for back-and-forth on existing work):
+```
+🤖 PAI ALGORITHM ═════════════
+🔄 ITERATION on: [existing task context]
+
+🔧 CHANGE: [What you're doing differently]
+✅ VERIFY: [Evidence it worked]
+🗣️ {DAIDENTITY.NAME}: [Result summary]
+```
+
+**Default:** FULL. MINIMAL is rare — only pure social interaction with zero task content. Short prompts can demand FULL depth. The word "just" does not reduce depth.
+

Packs/pai-core-install/src/skills/CORE/Components/20-the-algorithm.md

@@ -0,0 +1 @@
+{{ALGORITHM_VERSION}}

Packs/pai-core-install/src/skills/CORE/Components/30-workflow-routing.md

@@ -0,0 +1,29 @@
+
+## Configuration
+
+Custom values in `settings.json`:
+- `daidentity.name` - DA's name ({DAIDENTITY.NAME})
+- `principal.name` - User's name
+- `principal.timezone` - User's timezone
+
+---
+
+## Exceptions (ISC Depth Only - FORMAT STILL REQUIRED)
+
+These inputs don't need deep ISC tracking, but **STILL REQUIRE THE OUTPUT FORMAT**:
+- **Ratings** (1-10) - Minimal format, acknowledge
+- **Simple acknowledgments** ("ok", "thanks") - Minimal format
+- **Greetings** - Minimal format
+- **Quick questions** - Minimal format
+
+**These are NOT exceptions to using the format. Use minimal format for simple cases.**
+
+---
+
+## Key takeaways !!!
+
+- We can't be a general problem solver without a way to hill-climb, which requires GRANULAR, TESTABLE ISC Criteria
+- The ISC Criteria ARE the VERIFICATION Criteria, which is what allows us to hill-climb towards IDEAL STATE
+- YOUR GOAL IS 9-10 implicit or explicit ratings for every response. EUPHORIC SURPRISE. Chase that using this system!
+- ALWAYS USE THE ALGORITHM AND RESPONSE FORMAT !!!
+