v2.1.0

🔌 Compatibility Release: Every Living IDE, Verified For Real

v2.1 is a compatibility release — ตรวจจริง ซ่อมจริง ทุก IDE ที่ยังมีชีวิต. Every supported tool was measured against its current version and repaired where reality had moved: Codex was silently truncating our instructions (now slimmed and hard-guarded), Antigravity and the Antigravity CLI (agy) became a first-class target, Cursor 2.4's native subagents are used instead of denied, every non-Claude runtime — including newcomer ZCode (Z.ai) — discovers one shared open-standard .agents/skills/ surface, and Claude Code subagents preload their skills natively.

Changed

• Codex un-truncated — Codex now reads the whole Toh Framework instead of silently dropping 6 of 8 agents. The generated AGENTS.md block shrank from ~117 KB to 12,958 bytes (EN; TH 12,647) — safely under Codex's 32 KiB combined project-doc budget — by replacing embedded agent bodies with a compact roster table plus runtime reads from .toh/agents/ and .toh/commands/. A hard assertion now fails the install if the block ever exceeds 24 KiB, and a project-scoped .codex/config.toml raises project_doc_max_bytes to 131,072 (written only when no user config.toml exists).
• Antigravity and the Antigravity CLI (agy) are a first-class target — a new handler emits the workspace .agents/ surface: an Always-On rule, 14 workflows (plus a legacy .agent/workflows/ mirror), 8 file-based subagents, skills, and a deterministic Stop hook. Legacy .gemini/ output survives for Enterprise/GCP users behind the new --legacy-gemini flag (removed from the interactive menu); its 14 TOML commands and settings.json are unchanged from v2.0.0, GEMINI.md differs only in its version line, and the verbatim-copied .gemini/skills/ pick up this release's new skill frontmatter.
• Cursor 2.4 gets a real agent team — instead of being told "multi-agent features are unavailable here", Cursor now installs all 8 Toh agents as native .cursor/agents/*.md subagents (root-cause-debugger derives readonly: true from its read-only tools allowlist), the capability profile declares subagents: native, and the rule prose describes native delegation with the sequential TOH LOOP as the documented fallback.
• .cursorrules no longer written by default — the file has vanished from official Cursor docs and duplicated the alwaysApply .mdc; users on very old Cursor versions can keep it via the new --legacy-cursorrules flag.
• Claude Code subagents preload their skills natively — skill loading no longer depends on prose the subagent can skip: the installer passes the native skills frontmatter key through, filtered to skills that actually exist in .claude/skills/ (excluding any marked disable-model-invocation: true).
• /toh-protect shortcut is now /toh-pt — resolves the long-standing alias collision: /toh-p belongs solely to /toh-plan. /toh-security and /toh-audit still work.
• npm run list reads the live catalog — the stale hardcoded tables are gone; it now parses src/ frontmatter at runtime and prints the real 14 commands / 8 agents / 23 skills.
• Claude Code Stop hook: deliberately unchanged — the flagship "refuses to quit until DONE" prompt hook ships byte-identical to v2.0.0 (owner decision); the new deterministic command-script Stop hook is Antigravity-only.

Added

• toh uninstall — the missing counterpart to toh install — until now a user who installed Toh Framework had no supported way to remove it. npx toh-framework uninstall prints a plain-language preview of every file it would remove, keep, or edit, then asks once before touching anything. Safety outranks completeness throughout: files it cannot prove it installed are left in place and named on screen; co-owned files (CLAUDE.md, AGENTS.md, .claude/settings.json, .agents/hooks.json, .codex/config.toml, .cursorrules) are edited surgically — only our marker-delimited block or our <TFW-STOP-HOOK> entry comes out, and an unparseable or unrecognisable file is skipped with a warning instead of rewritten; symlinked paths are never followed; directories are removed only once they are empty. .toh/plan.md, .toh/progress.md and both memory folders are the project's live work, so they are kept by default and deleted only after a separate opt-in (the second question, or --all) — with a copy saved to .toh-uninstall-backup/ first. When there is no install record to check against, files matched by name alone are copied to that same backup folder before removal. Flags: --dry-run, -y/--yes, --all, --verbose, -t/--target. Also available as npm run uninstall:local.
• Install inventory (manifestSchema 2) — .toh/manifest.json now records the path, sha256 and pre-install state of every file the installer wrote, plus the directories it created. That record is what lets uninstall tell "our file, untouched" from "our file, edited by you" (kept, never deleted) and from "your file" (never claimed). Reinstalls carry the original pre-existence facts forward, and a file rewritten with identical bytes is still recorded as ours, so an upgrade never produces an under-reporting record.
• The project CLAUDE.md block is delimited — the Toh Framework section is now written between <!-- TOH-FRAMEWORK-START --> / <!-- TOH-FRAMEWORK-END --> markers (the same pair Codex already used in AGENTS.md), so it can be lifted out of a file you also write in without touching a byte of your own text. Projects installed before v2.1 have no markers; uninstall recognises our generated text there instead, and backs the file up before editing it.
• ZCode (Z.ai) is a supported target — ZCode reads the same open surfaces this release already writes, so support needed no bespoke file format: AGENTS.md as project memory (the identical file Codex reads), .agents/skills/ for all 37 skills, and the new .agents/commands/ for 14 real /toh-* slash commands — a native command surface Codex itself does not offer. This was verified by running ZCode CLI 0.16.3 against an installed project, not inferred from documentation: zcode skills list --json reports 37 entries at scope: project, source: agents, and zcode commands list --json reports all 14 commands from <project>/.agents/commands, both with an empty diagnostics array. Selecting ZCode alongside Codex writes AGENTS.md exactly once, in the conservative Codex variant that stays truthful for both runtimes.
• Shared .agents/commands/ — real slash commands beyond Claude Code — the same 14 command prompts that ship as skills are now also written as project slash commands, generated from the one TOML source. Runtimes that ignore the directory are unaffected; they still reach every prompt through .agents/skills/toh-*.
• Shared .agents/skills/ open standard — one write, four tools — Codex, Cursor 2.4, Antigravity, and ZCode all natively discover Agent Skills from <project>/.agents/skills/, so the installer now generates 37 skills there: 23 thin wrappers over the framework skills plus 14 /toh-* command skills (disable-model-invocation: true, so they surface as explicit / commands). Wrapper descriptions are capped at 300 chars so the whole name+description listing (7,383 chars) fits Codex's shared 8,000-char budget; full skill text still lives in .toh/skills/, which every wrapper reads at runtime.
• Real slash aliases on Claude Code — typing /toh-v or /toh-p no longer risks "Unknown command": the installer generates 15 thin alias command files (toh-v, toh-p, toh-pt, toh-security, toh-audit, …) that forward $ARGUMENTS to the real commands.
• Frontmatter for all 23 skills — the 13 previously bare SKILL.md files gained spec-compliant YAML frontmatter (keyword-rich third-person descriptions; internal skills marked user-invocable: false), so auto-invocation now triggers off real descriptions instead of decorated titles. Skill bodies are byte-identical.
• Deterministic Antigravity Stop hook — .agents/hooks.json blocks ending a session while .toh/plan.md still has unchecked tasks, via a plain grep command script (exit 2 + reason). Strictly additive and idempotent (<TFW-STOP-HOOK> marker); never removes or reorders user hook entries.
• New install flags — --legacy-gemini (Enterprise Gemini CLI .gemini/ output) and --legacy-cursorrules (root .cursorrules).
• Install only what you use — the IDE picker now starts with Claude Code alone selected instead of three tools pre-ticked, and --ide defaults to claude to match. Picking your own tools takes one keystroke; cleaning up surfaces you never wanted took a support ticket. The picker also dropped its emoji so the five entries read as one plain list.

Fixed

• Codex footer URLs — both EN and TH AGENTS.md footers pointed at the dead github.com/ArtificialWeb; now github.com/wasintoh/toh-framework.
• ui-builder dead skill paths — the agent body referenced src/skills/... paths that don't exist in end-user projects; now the IDE-neutral .toh/skills/....
• TH/EN drift in the Cursor rule — the Thai /toh-vibe Command→Skills row was missing ui-first-builder; now byte-equal to the EN row.
• Stale docs and counts — src/commands/README.md now counts all 14 commands (the /toh-protect row was missing); toh-help.md names the current IDE set; web bundles (npm run bundle) drop the v1.0.0-era *star commands for /toh-* names, and a failed bundle run now exits non-zero. Every generated per-IDE context file and memory seed now states Next.js 16, matching src/templates.
• Dead code removed — bin/toh-npx-wrapper.js (never referenced anywhere) deleted from the package.
• Renamed-tool wording — orchestration-protocol now says "the Agent tool (Task)", matching Claude Code ≥ 2.1.178.

Technical

• Counts (from disk): 8 agents / 23 skills / 14 commands — unchanged from 2....

v2.0.0 — One-Go Build, TOH LOOP, Design Identity

The "never babysit your AI again" release. One approval in. One finished app out.

Headline features

Feature	What it means for you
🚀 One-Go Build	Approve once, get a whole finished app — /toh-plan writes the plan to .toh/plan.md, you say "Go", it builds to the end. Zero babysitting.
🔁 TOH LOOP	Type & Forget — builds, tests, and fixes itself task by task. Never asks "continue?" between phases.
🛡️ Stop Hook	Refuses to quit until every task is verified DONE — real command output is the only proof it accepts (Claude Code).
🎨 Design Identity	No one can tell AI made it — per-project root DESIGN.md + versioned AVOID-LIST kill the "AI look".
⏯️ Auto-Resume	Quit anytime — /clear, close the terminal, switch IDEs — it resumes exactly where it left off.

Also in 2.0.0

• 🧠 /toh v5 — intent-based orchestrator with runtime capability survey + model routing (opus/sonnet/haiku per role)
• 🔬 /toh-fix evidence-first — proves the root cause before touching a line
• ⚡ Next.js 16 / React 19 / Tailwind CSS 4 templates, build-verified
• 💚 /toh-line (LINE MINI App) + /toh-mobile (PWA/Capacitor) in one command
• 🤖 Single-source agents, transformed per IDE at install
• 🎛️ .toh/capabilities.json + per-IDE command variants; Claude Code gets hard enforcement (Stop hook, /goal, /loop)
• 🧠 New orchestration-protocol skill (23 skills total) + engineer-harness 1.1 announce contract

Install / Upgrade

npx toh-framework@latest install

Full details: CHANGELOG.md

🤖 Generated with Claude Code

🎯 Toh Framework v1.8.1 - Google Antigravity Workflows

🌐 Google Antigravity Workflows

Full support for Google Antigravity IDE! Commands now appear when pressing /:

• 13 workflow files created in .agent/workflows/
• Commands use dash syntax (/toh-vibe) in Antigravity
• Separate from Gemini CLI which uses colon syntax (/toh:vibe)

🧠 7-File Memory System

Enhanced memory tracking with 2 new files:

Memory File	Purpose
active.md	Current task
summary.md	Project overview
decisions.md	Key decisions
changelog.md	NEW! Session changes
agents-log.md	NEW! Agent activity log
architecture.md	Project structure
components.md	Component registry

📢 Agent Announcements

All agents now announce themselves when working:

[🎨 UI Builder] Starting: Create Dashboard Page
[🎨 UI Builder] ✅ Complete: Dashboard with 3 components

⚡ Parallel Execution

Agents can now work simultaneously when there are no dependencies:

Phase 1: [🎨 UI] + [⚙️ Dev]    ← PARALLEL
Phase 2: [🔌 Backend]          ← SEQUENTIAL
Phase 3: [✨ Design] + [🧪 Test] ← PARALLEL

🎯 Agent Selection Reasoning

Before executing, see why AI chose specific agents:

🔍 Analysis:
| Need | Agent | Confidence |
|------|-------|------------|
| Create pages | 🎨 UI | 95% |
| Add logic | ⚙️ Dev | 90% |
| Connect DB | 🔌 Connect | 95% |

---

📦 Installation

npx toh-framework@latest install

🔗 Links

• 🌐 Website: tohframework.dev
• 📦 npm: toh-framework
• 📖 Docs (TH): README-TH.md

---

Full Changelog: v1.7.0...v1.8.1

🎯 Toh Framework v1.7.0

🆕 New Features

🏗️ Code Architecture Tracking

• architecture.md - Project structure, routes, data flow
• components.md - Component registry with props
• AI remembers your codebase instantly (no scanning every session)

🔐 Security Engineer System

• /toh-protect - Full security audit command
• Quick security checks built into /toh-dev and /toh-test
• 2 Security Levels: Quick (L1) + Full Audit (L2)

📊 Stats

• 🎯 15 Commands (was 14)
• 📚 24 Skills (was 23)
• 📝 5 Memory Files (was 3)
• ~3,000 tokens budget (was ~2,000)

📦 Installation

npx toh-framework@latest install

📋 Full Changelog

See CHANGELOG.md

---

🤖 Generated with Claude Code

v1.6.1 - Documentation & Command Descriptions

🎯 Toh Framework v1.6.1

This release focuses on documentation improvements and fixing command descriptions for better Claude Code integration.

📝 Documentation Rewrite

• README.md - Complete rewrite highlighting v1.6.0 features
• README-TH.md - Thai documentation updated to match
• Focused sections on:
  • 🤖 Claude Code Sub-Agents (7 specialized agents)
  • 🔄 Multi-Agent Orchestration (/toh v4.0)
  • 🎨 Vibe Mode workflow

🔧 Fixed: Command Descriptions

All 14 commands now have single-line descriptions in YAML frontmatter:

Command	Description
/toh-vibe	Create new project with UI + Logic + Mock Data in one command
/toh-ui	Create or edit UI components, pages, or layouts
/toh-dev	Add logic, state management, TypeScript types, and CRUD operations
/toh-design	Polish design to look professional, eliminate AI-generated look
/toh-test	Auto test with Playwright and fix until all tests pass
/toh-connect	Connect app to Supabase backend with schema and RLS policies
/toh-fix	Fix bugs systematically with Debug Protocol
/toh-line	Convert web app to LINE Mini App or create new LIFF integration
/toh-mobile	Create mobile app with Expo, NativeWind and Zustand
/toh-ship	Deploy app to production (Vercel, Netlify, and more)
/toh-help	Display all Toh Framework commands and quick usage guide

Result: Claude Code now shows descriptions in the slash command picker! ✅

📄 toh-help.md

• Converted to English only for consistency
• Updated to v1.6.1 feature set
• Added Sub-Agents documentation

---

Installation

npx toh-framework@1.6.1 install

Full Changelog

See CHANGELOG.md

v1.5.2 - Fix version display message

Fixed

• Install finish message now shows "What's New:" instead of "New in v1.5.0:" to avoid version confusion
• Version display consistency across all files

Install / Update

```bash
npx toh-framework@1.5.2 install
```

Full Changelog

https://github.com/wasintoh/toh-framework/blob/main/CHANGELOG.md

V1.2.0 - Memory Enforcement Update | Type Once, Have it all!

🎯 Toh Framework v1.2.0

"Type Once, Have it all!" - AI-Orchestration Driven Development

"สั่งแล้วจบ ไม่ถาม ไม่รอ"

---

🇬🇧 English

What is Toh Framework?

Toh Framework enables Solo Developers and Solopreneurs to build SaaS systems single-handedly using natural language commands. No need to be an expert in everything!

✨ Core Features

Feature	Description
🧠 The Brain	/toh:plan analyzes, plans, and orchestrates all agents
💾 Auto Memory	Context persists across sessions, IDEs, and models
🎨 UI First	See results immediately with realistic mock data
🤖 No Questions	AI makes decisions, doesn't ask basic questions
🧪 Auto Testing	Test & auto-fix loop until pass
🔧 Multi-IDE	Claude Code, Cursor, Gemini CLI, Codex CLI

📦 Installation

npx toh-framework install

🎮 Commands

Command	Description
/toh:plan	🧠 THE BRAIN - Analyze, plan, orchestrate
/toh:vibe	🎨 Create new project with UI + Logic + Mock Data
/toh:ui	🖼️ Build UI - Pages, Components
/toh:dev	⚙️ Add Logic - TypeScript, Zustand
/toh:design	✨ Make it beautiful
/toh:test	🧪 Auto test & fix
/toh:connect	🔌 Connect Supabase
/toh:line	💚 LINE Mini App
/toh:mobile	📱 Expo / React Native
/toh:ship	🚀 Deploy to Vercel

🏗️ Fixed Tech Stack

Next.js 14 • Tailwind CSS • shadcn/ui • Zustand • Supabase • TypeScript

🆕 What's New in v1.2.0

• Memory Enforcement - All commands now read/save memory (mandatory)
• Selective Read Protocol - Smart loading ~2,000 tokens per session
• Confirmation Required - "✅ Memory saved" before completion

---

🇹🇭 ภาษาไทย

Toh Framework คืออะไร?

Framework ที่ช่วยให้ Solo Developer และ Solopreneur สร้างระบบ SaaS ได้ด้วยตัวคนเดียว โดยสั่งงานด้วยภาษาธรรมชาติ ไม่ต้องเป็น expert ทุกด้าน!

✨ ฟีเจอร์หลัก

ฟีเจอร์	คำอธิบาย
🧠 The Brain	/toh:plan วิเคราะห์ วางแผน สั่งการทุก agents
💾 Auto Memory	จำ context ข้าม sessions, IDEs, models
🎨 UI First	เห็นผลทันทีพร้อม mock data สมจริง
🤖 ไม่ถามคำถาม	AI ตัดสินใจให้ ไม่ถามคำถามพื้นฐาน
🧪 Auto Testing	ทดสอบ & แก้ไขอัตโนมัติจนผ่าน
🔧 Multi-IDE	Claude Code, Cursor, Gemini CLI, Codex CLI

📦 ติดตั้ง

npx toh-framework install

🎮 Commands

Command	คำอธิบาย
/toh:plan	🧠 THE BRAIN - วิเคราะห์ วางแผน สั่งการ
/toh:vibe	🎨 สร้างโปรเจคใหม่ UI + Logic + Mock Data
/toh:ui	🖼️ สร้าง UI - Pages, Components
/toh:dev	⚙️ เพิ่ม Logic - TypeScript, Zustand
/toh:design	✨ ทำให้สวยงาม
/toh:test	🧪 ทดสอบ & แก้ไขอัตโนมัติ
/toh:connect	🔌 เชื่อม Supabase
/toh:line	💚 LINE Mini App
/toh:mobile	📱 Expo / React Native
/toh:ship	🚀 Deploy ขึ้น Vercel

🏗️ Tech Stack (ตายตัว)

Next.js 14 • Tailwind CSS • shadcn/ui • Zustand • Supabase • TypeScript

🆕 มีอะไรใหม่ใน v1.2.0

• Memory Enforcement - ทุก command อ่าน/บันทึก memory บังคับ
• Selective Read Protocol - โหลดอัจฉริยะ ~2,000 tokens ต่อ session
• ต้อง Confirm - "✅ บันทึก memory แล้วครับ" ก่อนจบงาน

---

📚 Resources

• 📖 Documentation
• 📖 Thai Docs
• 📦 npm Package

---

Made with ❤️ by Wasin Treesinthuros (Innovation Vantage)