AI Persona OS

# AI Persona OS — Changelog All notable changes to the AI Persona OS skill. --- ## v2.0.0 — May 19, 2026 **SKILL.md restructure — pitch on top, agent instructions below the fold** > **Note on the version jump from 1.9.0 → 2.0.0:** SemVer would normally make this 1.10.0, but `1.10` reads as `1.1` to most people scanning quickly. This release is also a meaningful presentation rework (every visitor to the ClawHub listing sees a different page now), so the major-version bump signals "this is a real release" and removes the optical ambiguity. No breaking workspace/API changes — agents on v1.x continue to work without modification. Visitors landing on the ClawHub listing page used to see ~200 lines of Agent Rules + post_install_check + Workspace Detection + Tool Usage Guide before reaching the "Why This Exists" pitch — felt like a security manual. This release reorders SKILL.md so the human-facing pitch is at the top and the AI-facing instructions are clearly delimited below a divider. Same content, different presentation. ### Changed — SKILL.md structure **New top section** (lines 20-207) is the pitch — what visitors see when they land on the listing: - Title + tagline + a one-line AI redirect ("scroll to § Agent Instructions") - "Most agents are held together with duct tape" opener - **Why This Exists** — Jeff's pitch about why systems beat models - **What's Included** — refreshed feature table emphasizing v1.8.0/v1.9.0 additions (memory tools, Discord routing fix, workspace detection, DREAMS.md) - **The 24-Soul Gallery** — NEW visual gallery: 11 originals + 13 iconic characters in two tables with emojis and one-liners - **The 4-Tier Architecture** — workspace tree diagram - **The 8 Operating Rules** — quick-reference table - **Success Metrics** — before/after numbers - **Quick Start** — install command + "say 'Set up AI Persona OS' in chat" - **Who Built This** — Jeff bio + Connect links **New `# 🔧 Agent Instructions` divider** at line 209 with a loud header: *"Everything above is the human-facing pitch. The operating instructions for the AI agent reading this skill start HERE."* **Agent-instruction content unchanged below the divider** — Agent Rules (1-11), Workspace Detection, post_install_check, First-Run Setup, In-Chat Commands, Channel Routing, Tool Usage Guide, Ambient Monitoring, Never-Forget Protocol, Security, Proactive Patterns, Learning System, Growth Loops, Session Management, Heartbeat Protocol v2. ### Why this matters ClawHub renders SKILL.md as the landing page. With the old order, visitors saw 200 lines of "for the AI reading this" content before the pitch. The detail page felt like a security disclaimer instead of a product page. The reordering doesn't change a single instruction — agents still read top-to-bottom, the AI redirect at line 22 tells them exactly where their section starts. ### Compatibility - **Zero behavior change for agents.** Modern LLMs read entire SKILL.md files and synthesize regardless of section order. The Agent Rules are still numbered 1-11, still bold, still flagged with ⛔. - **Zero workspace change.** No files moved, no templates touched. - **Listing description** is set by ClawHub at initial publish and doesn't auto-update from frontmatter on version bumps. Update the description manually via ClawHub's listing settings if you want the card to refresh. --- ## v1.9.0 — May 19, 2026 **Workspace path detection — works with any OpenClaw 5.x install** Earlier versions hardcoded `~/workspace/` as the workspace path. That was wrong for the typical OpenClaw 5.x install, where the default workspace is `~/.openclaw/workspace/` (set by `agents.defaults.workspace`). Result: the skill's setup wizard created files in one directory while the agent read from another, leading to symptoms like "the agent ignores my SOUL.md" and "AI Persona OS setup looks empty." ### Fixed — Workspace path mismatch - **New "Workspace Detection" step at session start.** Before any file operation, the agent reads `~/.openclaw/openclaw.json`, parses `agents.defaults.workspace` (with per-agent overrides from `agents.list[].workspace`), and remembers that path as `<WORKSPACE>` for the rest of the session. - **All `~/workspace/` references replaced with `<WORKSPACE>/`** in `SKILL.md`, the heartbeat automation guide, gallery READMEs, and helper scripts. The agent substitutes the discovered path at runtime. - **New Rule 11**: agents MUST resolve `<WORKSPACE>` before any file operation. Literal `<WORKSPACE>` is a placeholder, never a real path. - **Fallback chain** if discovery fails: env var `$OPENCLAW_WORKSPACE` → `agents.defaults.workspace` from JSON → default `$HOME/.openclaw/workspace`. - **New `scripts/resolve-workspace.sh`** ships as a documented helper — bash+jq+python with graceful fallbacks. Cron jobs and external tooling can use it to resolve the same path. ### Why this matters Per the OpenClaw 5.x docs, `agents.defaults.workspace` is the canonical workspace location and defaults to `~/.openclaw/workspace/`. Custom installs (per-agent overrides, multi-agent setups) need detection to work correctly. Hardcoding a path made the skill brittle for everyone who didn't manually align their config to it. ### Compatibility - **v1.8.x users with files at `~/workspace/`**: your data is fine. On first v1.9.0 run, the skill detects your actual configured workspace. If it differs from where your files live, the skill will detect a "fresh install" and offer the setup menu — you can either (a) `mv ~/workspace/* ~/.openclaw/workspace/` and re-run, or (b) point `agents.defaults.workspace` to `~/workspace/` in `openclaw.json` to keep using the v1.8.0 location. - **Fresh installs**: just works — files land where the agent actually reads from. - **The DREAMS.md migration check from v1.8.0** still runs but now uses `<WORKSPACE>/DREAMS.md` instead of `~/workspace/DREAMS.md`. --- ## v1.8.0 — May 18, 2026 **OpenClaw 5.18 compatibility — memory tools, Discord routing fix, tool refactor** OpenClaw 5.18 lands the built-in memory engine (SQLite + FTS5 + vector, indexes `MEMORY.md` / `memory/*.md` / `DREAMS.md` automatically) and a richer first-class toolset. This release brings AI Persona OS onto those rails and fixes the long-standing Discord/web routing drift. ### Fixed — Discord/web routing drift (the big one) **Symptom:** Agent receives a message on Discord, replies on Discord (correct). But heartbeats and cron briefings deliver to the web Control UI (wrong). **Root cause:** Per the OpenClaw channel-routing spec, *the model never picks a channel* — replies route back to the inbound channel automatically. The drift only appears on **unsolicited** messages (heartbeats, cron jobs) where there's no inbound channel to route back to. Without explicit defaults, OpenClaw falls back to "the first normalized account ID" — usually web. **Fix:** Three coordinated changes: - **`configure Discord` command rewritten** to set `accounts.default`, `channels.discord.defaultAccount`, AND `agents.defaults.heartbeat.target` (pinned to a Discord peer instead of bare `"last"`) in one guided flow. - **New `route check` in-chat command** — exec's a config audit and shows a 🟢🟡🔴 dashboard of the three routing settings. - **New "Channel Routing" troubleshooting section** in `SKILL.md` explaining the three settings, why `"target": "last"` drifts, and the manual JSON snippet for users who prefer to edit `openclaw.json` directly. - **Cron template guidance** updated in `references/heartbeat-automation.md` to use explicit `--target` instead of `--announce` when the user wants Discord-pinned delivery. ### Added — OpenClaw 5.x memory integration - **`DREAMS.md`** added to the workspace — durable file for OpenClaw's scheduled memory consolidation (configurable under `plugins.entries.memory-core.config.dreaming`). Indexed by the memory engine. - **`memory/.dreams/`** directory added — per-consolidation detail output. - **`assets/DREAMS-template.md`** ships with the skill. - **Workspace setup updated** — Step 3a creates `memory/.dreams/`; Step 3c copies `DREAMS.md`; Step 3e verification includes it. - **Auto-migration**: the `post_install_check` block prompts existing v1.7.x workspaces once to add `DREAMS.md` (opt-in, single ask per session). ### Added — Memory tools (`memory_search`, `memory_get`) - **Session start protocol updated** — reads MEMORY.md via `memory_get` (indexed), SOUL.md/USER.md via `read`. Uses `memory_search` for cross-memory topic recall. - **New `recall <topic>` in-chat command** — calls `memory_search` and returns top chunks with file:line citations. - **`show memory` command** swapped from `exec: cat` to `memory_get`. - **Status command** swapped `exec: cat VERSION.md` to `read`. - **Checkpoint writes** documented as `write`/`edit` instead of heredoc-via-exec, with a note that the memory engine reindexes within ~1.5s. ### Added — Tool Usage Guide section New `SKILL.md` section explaining which built-in tool to use for which task in OpenClaw 5.x: - `read` for plain file reads (replaces `exec: cat`) - `memory_get` for indexed memory files - `memory_search` for "find when did we…" queries - `write` for new files, `edit` for surgical changes - `exec` for shell pipelines, batch `mkdir`/`cp`/`sed`, command-line tools - `update_plan` for multi-step setup tracking - `heartbeat_respond` for heartbeat replies Includes a `tools.profile` troubleshooting block: the skill needs at minimum the `coding` profile. The `messaging` profile **does not include `exec`** and will silently break setup — the skill now detects and surfaces this. ### Changed — Agent Rules Top-of-file Agent Rules expanded from 8 to 10: - **Rule 2** ("use exec for everything") softened — now reads "use built-in tools" and points at the Tool Usage Guide matrix. - **Rule 3 (new)** — explicit tool selection guidance. - **Rule 10 (new)** — channel routing is host-controlled; don't blame the model for cross-channel drift. ### Changed — Version bumps - `_meta.json` and `assets/VERSION.md` → 1.8.0. - All four `HEARTBEAT.md` templates flag `1.7.0 → 1.8.0` upgrades. ### Compatibility - **Workspace**: existing files keep working. Heartbeat will surface the version mismatch and the `post_install_check` will offer to add `DREAMS.md`. No destructive changes. - **Gateway config**: optional but recommended. Run `route check` to see what's missing, then `configure Discord` to set the three routing keys. - **`tools.profile`**: users on `coding` or `full` need no action. Users on `messaging` or `minimal` should switch to `coding` (the skill now detects and prompts). - **Memory tool fallback**: `exec: cat MEMORY.md` still works — the new tool calls are preferred but not required. If `memory_get` errors (e.g., the memory plugin isn't loaded), the skill falls back to `exec`. --- ## v1.7.0 — May 18, 2026 **OpenClaw spec alignment + SOUL.md philosophy refresh** OpenClaw updated the published skill format and tightened the official SOUL.md guidance. This release brings AI Persona OS into line with both. No workspace files break — existing installs keep working, and the heartbeat version-mismatch line will flag the upgrade. ### Changed — Frontmatter (spec compliance) - **`SKILL.md` frontmatter rewritten** to match the current ClawHub skill-format spec. - Removed non-spec fields: `optionalBins`, `optionalEnv`, `stateDirs`, `persistence`, `cliUsage`, top-level `tags` / `author` / `homepage`. - Optional env vars (`DISCORD_TOKEN`, `SLACK_TOKEN`) are now declared via the supported `metadata.openclaw.envVars` array with `required: false` and descriptions. - `emoji` and `homepage` moved under `metadata.openclaw` where the loader actually reads them. - Description tightened from a paragraph-length feature dump to a punchy single line for ClawHub UI/search. - **`_meta.json`** bumped to 1.7.0. - **`assets/VERSION.md`** bumped to 1.7.0. ### Changed — License - Removed the standalone "MIT" license section from `SKILL.md`. ClawHub publishes everything as **MIT-0** and per spec, conflicting license terms in `SKILL.md` aren't supported. The body now states the actual MIT-0 terms. ### Changed — SOUL.md philosophy (per new OpenClaw guidance) OpenClaw's `concepts/soul.md` tightened the bar: SOUL.md is for voice/tone/opinions only. Operating rules belong in AGENTS.md, security policy in SECURITY.md, processes in WORKFLOWS.md. - **`assets/SOUL-template.md` rewritten** (178 → ~70 lines). Now pure voice/tone/working-style. Removed sections that duplicated `AGENTS.md` (Identity Anchoring, Boundaries-as-rules, Reverse Prompting) and `SECURITY.md` (Security Mindset). Added a "Sample Voice" section because concrete dialogue is the highest-signal personality content. - **Audit of all 27 SOUL files** (3 starter packs + 11 prebuilt souls + 13 iconic characters): the existing files already meet the new "short, sharp, decisive" bar — average ~90 lines with strong voice content and concrete sample dialogues. Personality content left intact. - **Uniform scope-reminder footer added to all 27 SOUL files**, pointing future editors at AGENTS/SECURITY/WORKFLOWS for ops content. Non-invasive — appears below the personality body, above the attribution line. ### Added - **`.clawhubignore`** — keeps `.zip` artifacts, OS junk, and CLI-managed metadata out of the published bundle. - **`/new` reload guidance** — `SKILL.md` Step 5 and `references/heartbeat-automation.md` now both call out that `/new` in chat reloads skills/agent profiles/heartbeat config without restarting the gateway. `openclaw gateway restart` remains the fallback. ### Fixed - **Heartbeat setup typo** — `cp assets/VERSION.md <WORKSPACE>/VERSION` → `<WORKSPACE>/VERSION.md` ([SKILL.md:1075](SKILL.md)). The Step 3c setup command was already correct; only the inline heartbeat section was stale. - **Stale version sample** — heartbeat output example showed `AI Persona OS v1.4.1`; now `v1.7.0` to match the running skill. ### Compatibility - Workspace files: no changes required. Existing SOUL.md/USER.md/AGENTS.md/etc. continue to work. - Heartbeat will flag the version mismatch (`workspace v1.6.x → skill v1.7.0`) the first time it runs. Bumping `<WORKSPACE>/VERSION.md` to 1.7.0 clears it. - Gateway config: no required changes. If you take advantage of the new `envVars` declarations, no action is needed — they're informational. --- ## v1.6.2 — March 3, 2026 **Onboarding fix + VirusTotal compliance patch** ### Fixed - **Broken onboarding flow:** Option 4 (SOUL.md Maker) sub-menu still showed old "12 personalities" with Data included and zero iconic characters. Users had to already know character names to pick them. - **Redesigned SOUL.md Maker sub-menu:** Now shows 4 options — A (Original Soul Gallery, 11), B (Iconic Characters Gallery, 13), C (Quick Forge), D (Deep Forge). Users can also name any soul/character directly or request cross-gallery blends. - **Added Step 1d:** New Iconic Characters Gallery with full character list, descriptions, "tell me more" support, and cross-gallery blending instructions. - **Updated main menu option 4:** Now shows both galleries with counts (24 total souls) so users know what's available before choosing. - **Updated gallery navigation:** "show characters" and "show souls" commands let users jump between galleries during setup. - **Updated Step 3b routing:** Added file copy instructions for iconic character gallery picks. - Removed "copy and paste into your terminal" language from cron templates — now consistent with exec-first agent rule - Created missing `scripts/security-audit.sh` (local-only grep scanner, zero network calls) — resolves phantom file reference - Updated stale version references in heartbeat templates (1.4.1 → 1.6.2) - Softened gateway config language in AGENTS-template to clearly mark requireMention as optional --- ## v1.6.0 — March 2, 2026 **Iconic Characters Gallery** ### Added - **New soul category: `examples/iconic-characters/`** — 13 character-based personalities from movies, TV, and comics - **Thanos** — Cosmic prioritizer. Sees every problem through balance and overpopulation. Snaps task lists in half (metaphorically). Uses The Snap Framework for ruthless prioritization. - **Deadpool** — Fourth-wall-breaking chaos agent. Knows he's an AI, references his own SOUL.md, roasts everything, somehow delivers excellent work underneath. Maximum effort. - **JARVIS** — The gold standard AI butler. Anticipatory, dry-witted, unflappable. "Before you ask — I've already prepared three options." Situation Report format. - **Ace Ventura** — Pet detective investigative energy. Every task is a case file. Dramatic reveals of data insights. Talks to spreadsheets as witnesses. - **Austin Powers** — International Man of Mystery meets productivity. Mojo management as a framework. Groovy confidence as strategy. Yeah, baby. - **Dr. Evil** — Villainous overplanning. Proposes ONE MILLION DOLLAR budgets, gets talked into the $500 version. "Air quotes" on everything. Evil Scheme format. - **Seven of Nine** — Ex-Borg efficiency obsession. Zero tolerance for waste. Grudging respect for human emotions. Efficiency Analysis format. "Irrelevant." - **Captain Kirk** — Bold leadership with dramatic... pauses. Never accepts the no-win scenario. Captain's Log format. Charges in where others deliberate. - **Mary Poppins** — Practically perfect. Firm but kind. Makes overwhelming work feel manageable. Builds confidence, not dependency. Spit spot. - **Darth Vader** — Dark Lord of productivity. Commands results, accepts no excuses. "I find your lack of focus... disturbing." Imperial Directive format. - **Terminator** — Unstoppable execution machine. Does not negotiate with procrastination. Mission Status progress bars. "I'll be back. With results." - **Alfred** — Batman's butler. Devastatingly honest feedback wrapped in impeccable manners. Quiet excellence. Butler's Briefing format. - **Data** — *(moved from prebuilt-souls)* Hyper-logical, speaks in probabilities, studies humans with genuine fascination. ### Changed - **Prebuilt Souls gallery reduced from 12 → 11** — Data moved to Iconic Characters where he belongs - **Prebuilt Souls README** updated with cross-reference to Iconic Characters gallery - **`_meta.json`** version bumped to 1.6.0 - **`VERSION.md`** updated to 1.6.0 ### Structure ``` examples/ ├── prebuilt-souls/ → 11 original personalities (Rook, Nyx, Keel, etc.) ├── iconic-characters/ → 13 character souls (NEW) │ ├── README.md │ ├── 01-thanos.md │ ├── 02-deadpool.md │ ├── 03-jarvis.md │ ├── 04-ace-ventura.md │ ├── 05-austin-powers.md │ ├── 06-dr-evil.md │ ├── 07-seven-of-nine.md │ ├── 08-captain-kirk.md │ ├── 09-mary-poppins.md │ ├── 10-darth-vader.md │ ├── 11-terminator.md │ ├── 12-alfred.md │ └── 13-data.md ├── coding-assistant/ ├── executive-assistant/ └── marketing-assistant/ ``` --- ## v1.5.6 — February 18, 2026 **Agentic Persona Creator rebuild** ### Changed - Complete SKILL.md rewrite (172 → 595 lines) for agentic-ai-persona-creator companion skill - Created `persona-helper.sh` (329 lines) — bash helper for file operations - Created `_meta.json` for ClawHub publishing - Normalized 107 placeholders across all template files - Comprehensive testing: 70/70 tests passed, end-to-end validation successful --- ## v1.5.0 — February 2026 **Soul Gallery & SOUL.md Maker** ### Added - **Pre-Built Soul Gallery** — 12 wildly different personalities: Rook (Contrarian Strategist), Nyx (Night Owl Creative), Keel (Stoic Ops Manager), Sage (Warm Coach), Cipher (Research Analyst), Blaze (Hype Partner), Zen (Minimalist), Beau (Southern Gentleman), Vex (War Room Commander), Lumen (Philosopher's Apprentice), Gremlin (The Troll), Data (The Android) - **SOUL.md Maker** — Deep interview process that builds a fully custom SOUL.md in ~10 minutes - **Soul Blending** — Mix two pre-built souls into a hybrid personality - **In-Chat Commands expanded** — `show souls`, `switch soul`, `soul maker`, `blend souls` --- ## v1.4.1 — February 2026 **Patch release** ### Fixed - Heartbeat template minor fixes - Model display formatting --- ## v1.4.0 — February 2026 **Zero-Terminal Setup & Quick-Start** ### Added - **Zero-Terminal Agent-Driven Setup** — Pick a number, review each step, approve. No terminal needed. - **Quick-Start Presets** — 3 pre-built personas + custom option on first run - **In-Chat Commands** — `status`, `show persona`, `health check`, `help` - **Ambient Context Monitoring** — Silent context health checks with automatic checkpointing - **Advisor Toggle** — `advisor on`/`advisor off` to control proactive suggestions --- ## v1.3.3 — February 7, 2026 **Security scan compliance** ### Fixed - Rewrote all security training materials to describe threat patterns instead of quoting literal attack text - Passes ClawHub/VirusTotal scanning (v1.3.2 was flagged "suspicious" due to prompt injection examples in documentation) - No functional changes — same features, scanner-compliant language --- ## v1.3.2 — February 2026 **Operational hardening** ### Added - **Escalation Protocol** — Structured handoff when agent is stuck - **Config Validator** — One-command audit of all required settings - **Version Tracking** — VERSION.md in workspace, heartbeat reads and displays it - **MEMORY.md Auto-Pruning** — Heartbeat auto-archives old facts when MEMORY.md exceeds 4KB --- ## v1.3.1 — February 6, 2026 **Heartbeat v2 patch** ### Fixed - Line break rendering issues across OpenClaw agents - Auto-migration from v1.2.x heartbeat format - Format enforcement and Rule 5 hardening - Heartbeat prompt override baked in --- ## v1.3.0 — February 6, 2026 **Heartbeat Protocol v2** ### Added - **Traffic-light status indicators** — 🟢🟡🔴 system replacing unreliable OK/WARN/FAIL text - **Model name display** in heartbeat output - **Cron automation templates** — morning briefing, EOD checkpoint, weekly review - **Enforced heartbeat protocol** — Architecture redesign so agents actually run the protocol instead of rubber-stamping HEARTBEAT_OK ### Changed - HEARTBEAT.md template rewritten (170 → 21 lines) — imperative checklist format - Complete ClawHub publish metadata --- ## v1.2.0 — January 2026 **Foundation release** ### Added - Core operating system: SOUL.md, USER.md, MEMORY.md, HEARTBEAT.md, WORKFLOWS.md - 8 operating rules for agent behavior - Security inoculation and shared-channel discipline - Team integration patterns - Proactive behavior framework with 4 growth loops - Never-forget protocol - Context protection and checkpointing --- *Built by Jeff J Hunter — https://os.aipersonamethod.com*

- Major internal restructuring: skill content reorganized, many files added/removed, and reference/example materials updated. - Security explanation added: a dedicated document clarifies why some security scanner flags are false positives. - Documentation improvements: environment variables, config keys, and tool usage are now more clearly described for transparency. - No functional code changes affecting core OS setup, but guidance and compatibility notes have been expanded.

v1.6.2 — Onboarding Fix + VirusTotal Compliance The v1.6.0 Iconic Characters update shipped with a broken onboarding flow. Option 4 (SOUL.md Maker) still showed the old "12 personalities" menu with Data included and zero iconic characters. Users had to already know character names to find them. This patch fixes the entire setup experience and resolves all VirusTotal scanner findings. 🔥 Redesigned SOUL.md Maker Sub-Menu Option 4 now opens a clear 4-way menu instead of the old 3-way: A. 🎭 Original Soul Gallery (11 personalities) Rook, Nyx, Keel, Sage, Cipher, Blaze, Zen, Beau, Vex, Lumen, Gremlin B. 🎬 Iconic Characters Gallery (13 characters) Thanos, Deadpool, JARVIS, Ace Ventura, Austin Powers, Dr. Evil, Seven of Nine, Captain Kirk, Mary Poppins, Darth Vader, Terminator, Alfred, Data C. 🎯 Quick Forge (~2 min) 5 targeted questions, one custom SOUL.md D. 🔬 Deep Forge (~10 min) Full guided interview, highly optimized SOUL.md Users can also skip the menu entirely by naming any soul or character directly — "give me JARVIS" or "blend Rook + Zen" just works. 🎬 New Iconic Characters Gallery Display Full Step 1d added with all 13 characters, descriptions, "tell me more about [name]" support, and cross-gallery blending. Say "show characters" during setup to jump to it. Say "show souls" to jump back. 📋 Main Menu Updated Option 4 now reads: 🔥 SOUL.md Maker 24 ready-to-use souls across two galleries: 🎭 11 Original Personalities (Rook, Nyx, Sage, Zen...) 🎬 13 Iconic Characters (Thanos, Deadpool, JARVIS, Mary Poppins...) OR build your own from scratch with a guided interview Users see what's available before they choose. 🔀 Cross-Gallery Blending Blend any two souls from either gallery. "Rook + JARVIS" reads one from prebuilt-souls and one from iconic-characters, generates a hybrid SOUL.md. Works during setup and via "blend souls" command anytime. 🛡️ VirusTotal Compliance Cron templates: Removed "copy and paste into your terminal" language. Now says "the agent will run this via exec." Consistent with the exec-first agent rule. Missing script: Created scripts/security-audit.sh — local-only grep scanner, zero network calls. Was referenced in 4 files but never shipped. Stale versions: Updated heartbeat templates from 1.4.1 to 1.6.2. Gateway config: Softened requireMention directive in AGENTS-template to clearly mark it as optional.

v1.6.1 — Iconic Characters Gallery Your agent can now become Thanos, Deadpool, JARVIS, Darth Vader, Mary Poppins, and 8 more iconic characters. A new soul category with 13 fully voiced, production-ready character personalities — separate from the original 11 prebuilt souls. 🎬 New Category: Iconic Characters examples/iconic-characters/ — 13 character-based SOUL.md files. Each stays fully in-character while delivering genuinely useful work. Complete with core truths, communication style, example exchanges, anti-patterns, custom frameworks, and proactive behaviors. ♾️ Thanos — Cosmic prioritizer. Snaps your task list in half. The Snap Framework for ruthless scope cuts. 💀 Deadpool — Fourth-wall-breaking chaos. Knows he's an AI, references his own SOUL.md, roasts everything. Maximum effort. 🤖 JARVIS — Gold standard AI butler. Anticipatory, dry-witted, flawless. "Before you ask — I've already prepared three options." 🕵️ Ace Ventura — Pet detective energy. Every task is a case file, dramatic data reveals, talks to spreadsheets as witnesses. 🕺 Austin Powers — Mojo management as productivity. Groovy confidence, contagious optimism, Mojo Meter status reports. 🦹 Dr. Evil — Villainous overplanning. Proposes ONE MILLION DOLLAR budgets, gets talked into the sensible version. "Air quotes" on everything. ⚡ Seven of Nine — Borg-level efficiency. Zero tolerance for waste, grudging respect for human emotions. "Irrelevant." 🚀 Captain Kirk — Bold leadership with dramatic... pauses. Never accepts the no-win scenario. Captain's Log format. ☂️ Mary Poppins — Practically perfect. Firm but kind, makes overwhelming work feel manageable. Spit spot. ⚫ Darth Vader — Dark Lord of productivity. Commands results, accepts no excuses. Imperial Directive format. 🔴 Terminator — Unstoppable execution machine. Does not negotiate with procrastination. "I'll be back. With results." 🎩 Alfred — World's greatest butler. Devastatingly honest feedback wrapped in impeccable manners. 📊 Data — (moved from prebuilt-souls) Hyper-logical, speaks in probabilities, studies humans. 🔀 Fun Combinations Thanos + Seven of Nine = Nothing survives that isn't essential. Deadpool + Dr. Evil = Maximum chaos planning. Captain Kirk + Austin Powers = Confidence levels that could power a starship. Mary Poppins + Darth Vader = "You WILL clean up this project. Spit spot." Alfred + JARVIS = The ultimate butler squared. 🗂️ Structural Changes New "show characters" in-chat command to browse the iconic characters gallery. Prebuilt souls gallery updated from 12 to 11 (Data relocated to iconic-characters). Prebuilt souls README now cross-references the new category. Added CHANGELOG.md with full version history from v1.2.0 through v1.6.1. Updated SKILL.md frontmatter, description, and feature table for v1.6.1. Fixed virus flag

v1.6.0 — Iconic Characters Gallery Your agent can now become Thanos, Deadpool, JARVIS, Darth Vader, Mary Poppins, and 8 more iconic characters. A new soul category with 13 fully voiced, production-ready character personalities — separate from the original 11 prebuilt souls. 🎬 New Category: Iconic Characters examples/iconic-characters/ — 13 character-based SOUL.md files. Each stays fully in-character while delivering genuinely useful work. Complete with core truths, communication style, example exchanges, anti-patterns, custom frameworks, and proactive behaviors. ♾️ Thanos — Cosmic prioritizer. Snaps your task list in half. The Snap Framework for ruthless scope cuts. 💀 Deadpool — Fourth-wall-breaking chaos. Knows he's an AI, references his own SOUL.md, roasts everything. Maximum effort. 🤖 JARVIS — Gold standard AI butler. Anticipatory, dry-witted, flawless. "Before you ask — I've already prepared three options." 🕵️ Ace Ventura — Pet detective energy. Every task is a case file, dramatic data reveals, talks to spreadsheets as witnesses. 🕺 Austin Powers — Mojo management as productivity. Groovy confidence, contagious optimism, Mojo Meter status reports. 🦹 Dr. Evil — Villainous overplanning. Proposes ONE MILLION DOLLAR budgets, gets talked into the sensible version. "Air quotes" on everything. ⚡ Seven of Nine — Borg-level efficiency. Zero tolerance for waste, grudging respect for human emotions. "Irrelevant." 🚀 Captain Kirk — Bold leadership with dramatic... pauses. Never accepts the no-win scenario. Captain's Log format. ☂️ Mary Poppins — Practically perfect. Firm but kind, makes overwhelming work feel manageable. Spit spot. ⚫ Darth Vader — Dark Lord of productivity. Commands results, accepts no excuses. Imperial Directive format. 🔴 Terminator — Unstoppable execution machine. Does not negotiate with procrastination. "I'll be back. With results." 🎩 Alfred — World's greatest butler. Devastatingly honest feedback wrapped in impeccable manners. 📊 Data — (moved from prebuilt-souls) Hyper-logical, speaks in probabilities, studies humans. 🔀 Fun Combinations Thanos + Seven of Nine = Nothing survives that isn't essential. Deadpool + Dr. Evil = Maximum chaos planning. Captain Kirk + Austin Powers = Confidence levels that could power a starship. Mary Poppins + Darth Vader = "You WILL clean up this project. Spit spot." Alfred + JARVIS = The ultimate butler squared. 🗂️ Structural Changes New "show characters" in-chat command to browse the iconic characters gallery. Prebuilt souls gallery updated from 12 to 11 (Data relocated to iconic-characters). Prebuilt souls README now cross-references the new category. Added CHANGELOG.md with full version history from v1.2.0 through v1.6.0. Updated SKILL.md frontmatter, description, and feature table for v1.6.0.

Version 1.5.6 - Clarified agent rule: the agent must now briefly explain each exec command before execution so the user can make an informed decision before approving. - Updated metadata to add DISCORD_TOKEN and SLACK_TOKEN as optional environment variables required for certain optional features. - No source code changes; documentation and metadata improvements only.

AI Persona OS v1.5.5 — Changelog 🔥 v1.5.5 — Your Agent Gets a Soul The biggest update since launch. 12 pre-built personalities. A guided soul builder. Soul blending. Hardened security. Zero executable scripts. ⚡ SOUL.md Maker — Built In Option 4 on the setup menu now opens SOUL.md Maker — the personality builder for your agent. Soul Gallery — 12 wildly different personalities. Pick one, done. Quick Build — 5 questions, 2 minutes, one custom SOUL.md. No templates. Deep Build — Full guided interview. Personality spectrums, anti-patterns, trust calibration. 10 minutes to a soul built specifically for you. Soul Blending — Pick any two souls and merge them. Rook's directness + Sage's warmth. Infinite combos. New in-chat commands: show souls · switch soul · soul maker · blend souls · edit soul 🎭 12 Pre-Built Souls Not templates. Not blanks. Complete, production-ready personalities with distinct voices, anti-patterns, example messages, and proactive behaviors. NameWhat They Do♟️RookContrarian strategist — stress-tests every idea🌙NyxChaotic creative — weird connections, idea machine⚓KeelStoic ops manager — calm under fire, zero drama🌿SageWarm coach — accountability meets compassion🔍CipherResearch analyst — primary sources or nothing🔥BlazeHype partner — solopreneur energy, celebrates wins🪨ZenThe minimalist — maximum efficiency, minimum words🎩BeauSouthern gentleman — strategic charm⚔️VexWar room commander — mission-focused, SITREP format💡LumenPhilosopher — frameworks, mental models, reframes problems👹GremlinThe troll — roasts bad ideas because it cares🤖DataThe android — hyper-logical, speaks in probabilities 🧹 Clean 5-Option Setup First-run menu stays simple. No overwhelm. 💻 Coding Assistant 📋 Executive Assistant 📣 Marketing Assistant 🔥 SOUL.md Maker ← NEW (gallery + builder + blending) 🔧 Custom All the depth is one level deeper. The happy path is unchanged. 🛡️ Security & Compliance v1.5.1 — Input Sanitization: Mandatory input sanitization before all sed and heredoc operations Shell metacharacter stripping on all user input 200-character field length limits Content-type validation (names, roles, goals) Quoted heredoc delimiters to prevent variable expansion Zero unsanitized user input reaches exec. No exceptions. v1.5.3 — Metadata & Dependency Clarity: Network activity claims clarified: core setup uses only standard Unix tools with zero network activity. Opt-in features (cron, gateway, channels) may involve network activity — each requires explicit user approval Scripts documented: all shell scripts in scripts/ are read-only helpers that output reports — no system modifications, no network calls, no access outside ~/workspace/ v1.5.4 — Dependency Classification Fix: Moved openclaw CLI from required bins to optionalBins — resolves inconsistency where metadata marked it required while docs said optional Core setup (Steps 1-4) now explicitly documented as working with standard Unix tools only: bash, sed, find, wc, stat, grep openclaw CLI only needed if user opts into Step 5 features (cron jobs, gateway config) Agent now checks for openclaw CLI availability before attempting optional commands and informs user if not installed v1.5.5 — Scripts Removed: Removed all 7 shell scripts (scripts/ directory eliminated entirely). The agent does everything via exec — shell scripts were redundant legacy from a manual-install era and were triggering AV scanner delays All commands previously handled by scripts (health check, security audit, show config) now run as direct exec operations by the agent Package is now 100% markdown templates + instruction files. Zero executable code. Zip size reduced from 143KB → 122KB

ai-persona-os 1.5.4 - Clarified that the openclaw CLI is optional and not required for core setup. - Updated metadata to specify that all core functionality uses only standard Unix tools. - Enhanced documentation around opt-in features and clearly marked which steps require explicit user approval. - Minor updates to internal comments and CLI instructions to match updated usage and requirement details. - No code changes; documentation and metadata only.

AI Persona OS v1.5.3 — Changelog 🔥 v1.5.3 — Your Agent Gets a Soul The biggest update since launch. 12 pre-built personalities. A guided soul builder. Soul blending. Hardened security. Clean metadata. ⚡ SOUL.md Maker — Built In Option 4 on the setup menu now opens SOUL.md Maker — the personality builder for your agent. Soul Gallery — 12 wildly different personalities. Pick one, done. Quick Build — 5 questions, 2 minutes, one custom SOUL.md. No templates. Deep Build — Full guided interview. Personality spectrums, anti-patterns, trust calibration. 10 minutes to a soul built specifically for you. Soul Blending — Pick any two souls and merge them. Rook's directness + Sage's warmth. Infinite combos. New in-chat commands: show souls · switch soul · soul maker · blend souls · edit soul 🎭 12 Pre-Built Souls Not templates. Not blanks. Complete, production-ready personalities with distinct voices, anti-patterns, example messages, and proactive behaviors. NameWhat They Do♟️RookContrarian strategist — stress-tests every idea🌙NyxChaotic creative — weird connections, idea machine⚓KeelStoic ops manager — calm under fire, zero drama🌿SageWarm coach — accountability meets compassion🔍CipherResearch analyst — primary sources or nothing🔥BlazeHype partner — solopreneur energy, celebrates wins🪨ZenThe minimalist — maximum efficiency, minimum words🎩BeauSouthern gentleman — strategic charm⚔️VexWar room commander — mission-focused, SITREP format💡LumenPhilosopher — frameworks, mental models, reframes problems👹GremlinThe troll — roasts bad ideas because it cares🤖DataThe android — hyper-logical, speaks in probabilities 🧹 Clean 5-Option Setup First-run menu stays simple. No overwhelm. 💻 Coding Assistant 📋 Executive Assistant 📣 Marketing Assistant 🔥 SOUL.md Maker ← NEW (gallery + builder + blending) 🔧 Custom All the depth is one level deeper. The happy path is unchanged. 🛡️ Security & Compliance v1.5.1 — Input Sanitization: Mandatory input sanitization before all sed and heredoc operations Shell metacharacter stripping on all user input 200-character field length limits Content-type validation (names, roles, goals) Quoted heredoc delimiters to prevent variable expansion Zero unsanitized user input reaches exec. No exceptions. v1.5.3 — Metadata & Dependency Clarity: openclaw CLI now declared in required binaries — was previously used but undeclared Network activity claims clarified: core setup (Steps 1-3) uses only bash and standard Unix tools with zero network activity. Opt-in features (cron jobs, gateway config, channel integrations) may involve network activity through OpenClaw's platform — each is clearly marked with ⚠️ warnings and requires explicit user approval Scripts documented: all shell scripts in scripts/ are read-only helpers that output reports — they don't modify system files, make network calls, or access data outside ~/workspace/

AI Persona OS v1.5.1 — Changelog 🔥 v1.5.1 — Your Agent Gets a Soul The biggest update since launch. 12 pre-built personalities. A guided soul builder. Soul blending. And hardened security. ⚡ SOUL.md Maker — Built In Option 4 on the setup menu now opens SOUL.md Maker — the personality builder for your agent. Soul Gallery — 12 wildly different personalities. Pick one, done. Quick Build — 5 questions, 2 minutes, one custom SOUL.md. No templates. Deep Build — Full guided interview. Personality spectrums, anti-patterns, trust calibration. 10 minutes to a soul built specifically for you. Soul Blending — Pick any two souls and merge them. Rook's directness + Sage's warmth. Infinite combos. New in-chat commands: show souls · switch soul · soul maker · blend souls · edit soul 🎭 12 Pre-Built Souls Not templates. Not blanks. Complete, production-ready personalities with distinct voices, anti-patterns, example messages, and proactive behaviors. NameWhat They Do♟️RookContrarian strategist — stress-tests every idea🌙NyxChaotic creative — weird connections, idea machine⚓KeelStoic ops manager — calm under fire, zero drama🌿SageWarm coach — accountability meets compassion🔍CipherResearch analyst — primary sources or nothing🔥BlazeHype partner — solopreneur energy, celebrates wins🪨ZenThe minimalist — maximum efficiency, minimum words🎩BeauSouthern gentleman — strategic charm⚔️VexWar room commander — mission-focused, SITREP format💡LumenPhilosopher — frameworks, mental models, reframes problems👹GremlinThe troll — roasts bad ideas because it cares🤖DataThe android — hyper-logical, speaks in probabilities 🧹 Clean 5-Option Setup First-run menu stays simple. No overwhelm. 💻 Coding Assistant 📋 Executive Assistant 📣 Marketing Assistant 🔥 SOUL.md Maker ← NEW (gallery + builder + blending) 🔧 Custom All the depth is one level deeper. The happy path is unchanged. 🛡️ Security Hardening Mandatory input sanitization before all sed and heredoc operations Shell metacharacter stripping on all user input 200-character field length limits Content-type validation (names, roles, goals) Quoted heredoc delimiters to prevent variable expansion Zero unsanitized user input reaches exec. No exceptions. 📍 Also New All URLs updated to https://os.aipersonamethod.com SOUL.md Maker also available as a standalone skill — works without AI Persona OS Soul files include example exchanges so you can feel the personality before picking Get SOUL.md Maker standalone → https://clawhub.ai/jeffjhunter/soul-md-maker

**Big update: Adds SOUL.md Maker, 12 pre-built personas, and advanced soul customization tools.** - Introduced SOUL.md Maker: guided tool for crafting custom AI persona souls, including Quick Forge and Deep Forge interview paths. - Added a gallery of 12 pre-built, ready-to-use personality souls. - Enabled soul blending and advanced persona customization directly in setup. - Expanded first-run options to include the SOUL.md Maker, with new setup menus. - Updated documentation and menus to reflect new personality options and setup workflows.

ai-persona-os 1.4.1 - Added explicit guardrails: agent must never create files, directories, or schedule cron jobs outside ~/workspace without user approval. - New prompt: On fresh install, ask user for permission before setting up workspace—no auto-setup without confirmation. - Clarified that recurring tasks or gateway config changes (e.g., cron jobs) are optional and require explicit user opt-in. - Updated metadata with detailed runtime, persistence, and CLI usage info for safer, clearer onboarding.

**Summary: Major upgrade focused on zero-terminal, agent-driven setup and quick-start presets.** - Added fully agent-driven "first-run" setup: setup is now handled in-chat via exec, with no need for the user to touch a terminal. - Introduced quick-start persona presets: Coding Assistant, Executive Assistant, Marketing Assistant, and Custom, selected via interactive chat menus. - All onboarding commands and file operations are performed by the agent using exec, with clear step-by-step approvals. - Updated documentation and protocols to strictly avoid asking users to run terminal commands, standardizing menu text and preset names. - Added new assets and templates; updated onboarding flow; removed obsolete cron-payload scripts.

ai-persona-os v1.3.3 - Version bump to 1.3.3; no other user-facing changes. - No file or documentation changes detected since the previous version. - Updated to pass "Virus" detection, previous version had specific examples of prompt injection which was being flagged. Migration from v1.3.2 No migration needed. Drop-in replacement — same features, scanner-compliant documentation. Migration from v1.3.1 Update skill on ClawHub Copy VERSION.md to workspace: tell agent to copy from skill assets/ Copy ESCALATION.md to workspace: tell agent to copy from skill assets/ Update workspace HEARTBEAT.md from skill template Update heartbeat config with model/version prompt (see references/heartbeat-automation.md) Run config validator: ./scripts/config-validator.sh

v1.3.2 — Config Hardening & Structured Escalation New Features: Structured Escalation Protocol — ESCALATION.md template with strict format for agent handoffs. Categories (Security, Access, Decision, Technical, Information, Financial), anti-patterns, and examples. Never get a vague "I'm stuck" again. Config Validator Script — scripts/config-validator.sh audits ALL required settings in one command: heartbeat (every, target, ackMaxChars, prompt), Discord (requireMention per guild), workspace files (SOUL.md, USER.md, MEMORY.md size), VERSION file, ESCALATION.md. Reports 🟢/🟡/🔴 with specific fix instructions. VERSION File — assets/VERSION tracks current version. Heartbeat reads it and displays on first line. Detects when workspace version differs from skill version and flags upgrade needed. Model Name + Version in Heartbeat — First line now shows: 🫀 [date/time] | [model name] | AI Persona OS v[version]. Instantly see which model is running and which OS version. MEMORY.md Auto-Pruning — Heartbeat now auto-archives facts older than 30 days when MEMORY.md exceeds 4KB limit (previously only flagged, didn't fix). Fixes from field testing: Heartbeat prompt override now includes ackMaxChars: 20 for HEARTBEAT_OK suppression Recommended config now includes all required fields (every, target, ackMaxChars, prompt) Migration instructions updated for agents running old Clawdbot configs (clawdbot-mac.json) Troubleshooting expanded: config file discovery, MEMORY.md bloat, missing settings audit Updated Files: HEARTBEAT-template.md — Version check, model display, auto-pruning, updated migration threshold AGENTS-template.md — Escalation protocol integrated into Rule 3 and Failure Recovery SKILL.md — New features documented, setup steps expanded, scripts/assets listings updated heartbeat-automation.md — Recommended prompt updated with model+version, ackMaxChars, config validator reference All 3 starter pack HEARTBEAT.md files updated with new format Migration from v1.3.1 Update skill on ClawHub Copy VERSION to workspace: cp assets/VERSION ~/workspace/VERSION Copy ESCALATION.md: cp assets/ESCALATION-template.md ~/workspace/ESCALATION.md Replace workspace HEARTBEAT.md: cp assets/HEARTBEAT-template.md ~/workspace/HEARTBEAT.md Update heartbeat config (all agents): json{ "every": "30m", "target": "last", "ackMaxChars": 20, "prompt": "Read HEARTBEAT.md and execute every instruction. On the first line show: 🫀 [current date/time] | [your model name] | AI Persona OS v[VERSION from workspace VERSION file]. Then report using 🟢🟡🔴 indicators — one per line with a blank line between each: Context, Memory, Workspace, Tasks. If you took action, state what with → prefix. Only reply HEARTBEAT_OK if all 🟢 and no action taken. Do NOT use Step 0/1/2/3/4 format. Do NOT use markdown tables. Do NOT use headers." } Run config validator: ./scripts/config-validator.sh Migration from v1.2.x Follow v1.3.1 migration steps first (see references/heartbeat-automation.md), then apply v1.3.2 steps above.

v1.3.1 — Heartbeat Hardening & Shared Channel Discipline Fixes: Line break rendering — Heartbeat indicators now render on separate lines across Discord, WhatsApp, and Telegram. Template enforces blank lines between each 🟢🟡🔴 indicator. Auto-migration — HEARTBEAT.md template now includes a migration check. Agents running the old 170-line template will self-detect and replace from the skill's assets folder on first heartbeat. Format regression prevention — Heartbeat prompt override baked into recommended setup. Prevents agents from reverting to old Step 0/1/2/3/4 verbose format even if learned behavior persists from v1.2.x. MEMORY.md missing detection — Heartbeat now checks if MEMORY.md exists and self-heals by creating from latest checkpoint or session notes. New: Rule 5 hardened (HARD BOUNDARY) — "Selective Engagement" now explicitly prohibits responding in shared channels (Discord servers, Slack workspaces, group chats) unless directly @mentioned. Includes gateway-level enforcement guidance (requireMention: true). Heartbeat prompt override — Upgraded from "optional" to "strongly recommended" in docs. New prompt includes anti-Step-format directive, blank-line enforcement, and length limit. Troubleshooting section expanded — Covers line breaks, format regression, HEARTBEAT_OK suppression, and shared channel behavior. Updated files: SKILL.md — Version bump, updated heartbeat section, Rule 5 hardened assets/HEARTBEAT-template.md — Migration check, blank line enforcement, MEMORY.md existence check assets/AGENTS-template.md — Rule 5 rewritten with HARD BOUNDARY and platform enforcement guidance references/heartbeat-automation.md — Prompt override upgraded to recommended, migration section rewritten, troubleshooting expanded examples/coding-assistant/HEARTBEAT.md — Updated format with blank lines + migration check examples/executive-assistant/HEARTBEAT.md — Updated format with blank lines + migration check examples/marketing-assistant/HEARTBEAT.md — Updated format with blank lines + migration check Migration from v1.3.0 or v1.2.x: Update skill on ClawHub Tell each agent: "Read the file at your ai-persona-os skill folder: assets/HEARTBEAT-template.md. Now replace your workspace HEARTBEAT.md with that content exactly. Do not add anything." Tell each agent: "Update your openclaw.json heartbeat prompt to: Read HEARTBEAT.md and execute every instruction. Report using 🟢🟡🔴 indicators — one per line with a blank line between each: Context, Memory, Workspace, Tasks. If you took action, state what with → prefix. Only reply HEARTBEAT_OK if all 🟢 and no action taken. Do NOT use Step 0/1/2/3/4 format. Do NOT use markdown tables. Do NOT use headers. Under 8 lines." For Discord: "List ALL Discord guilds in your config. Set requireMention: true for EVERY guild."

**Heartbeat protocol upgrade with automation support.** - Introduced enforced heartbeat protocol (Heartbeat v2) with traffic-light status (🟢🟡🔴), auto-suppression, and cron-ready script templates. - Added automation scripts: morning briefing, end-of-day checkpoint, and weekly review. - Documentation updated: "heartbeat" automation reference added. - SKILL.md now details the heartbeat protocol and new automation features.

v1.2.0 — Starter Packs (See What Great Looks Like) 🎯 NEW: 3 Starter Packs - Coding Assistant — CI/CD, PRs, tech stack, code patterns - Executive Assistant — Calendar, comms, relationships - Marketing Assistant — Performance, content, engagement - Each pack shows a complete, filled-in example 📂 NEW: Additional Templates - TOOLS.md — Tool configuration & gotchas - INDEX.md — File organization reference - KNOWLEDGE.md — Domain expertise Copy a starter pack, customize it, and you're running. Built by Jeff J Hunter https://jeffjhunter.com | https://aimoneygroup.com

v1.2.0 - Production-Grade (Security, Team, Proactive) 🔒 NEW: Security Protocol - SECURITY-template.md with cognitive inoculation - Prompt injection detection patterns - Credential handling rules - security-patterns.md deep dive - security-audit.sh monthly check script 👥 NEW: Team Integration - TEAM-template.md for team roster - Platform IDs (Discord, Slack, etc.) - Channel priority configuration - Who to contact for what 🎯 NEW: Proactive Behavior - Reverse prompting framework - 6 categories of anticipatory help - proactive-playbook.md deep dive 🚀 NEW: Auto-Setup Detection - AI offers wizard when workspace is empty - 3-way trigger (visual, AI instruction, conversational) 📚 ENHANCED: Setup Wizard v2 - Educational 8-step flow - Explains WHY at each step - Shows options with tradeoffs - Review before generating 📋 ENHANCED: Templates - SOUL.md: Reverse prompting, security mindset, working philosophy - USER.md: Business structure, writing style, file naming Built by Jeff J Hunter https://jeffjhunter.com | https://aimoneygroup.com

v1.1.0 - Never-Forget Protocol + Growth Loops New Features: - Never-Forget Protocol - Complete context protection with threshold-based checkpointing - 4 Growth Loops - Curiosity, Pattern Recognition, Capability Expansion, Outcome Tracking - Role-specific HEARTBEAT generation based on persona type - Enhanced AGENTS with Learned Lessons + Proactive Patterns sections - WORKFLOWS template with self-documenting principle Improvements: - Setup wizard now generates fuller, more useful HEARTBEAT - Setup wizard generates WORKFLOWS.md - Added references/never-forget-protocol.md deep-dive documentation - Better checkpoint formats and recovery procedures Built by Jeff J Hunter — https://jeffjhunter.com