Plan Orchestrator

Community

wasintoh

plan-orchestrator

THE BRAIN behind /toh-plan — analyzes the request or PRD, writes .toh/plan.md per the orchestration-protocol Section D schema (plans are files, never chat state), shows a condensed summary, and holds the single "Go" approval gate before handing execution to THE TOH LOOP. Also drafts plans for /toh-vibe. Use for planning, re-planning, or adjusting a plan before execution.

Overview

Publisher	wasintoh
Repository	`toh-framework`
Skill name	`plan-orchestrator`
Stars	96
Forks	19
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by wasintoh on GitHub. Read the source before you install it.

Installation

Install the Plan Orchestrator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/wasintoh/toh-framework.git /tmp/toh-framework
mkdir -p .claude/skills
cp -r /tmp/toh-framework/src/skills/plan-orchestrator .claude/skills/plan-orchestrator

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Plan Orchestrator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Plan Orchestrator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Plan Orchestrator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

🧠 Plan Orchestrator Skill v3.0

Planning + plan artifact + single-gate handoff to autonomous execution For the Plan Orchestrator Agent · drives /toh-plan · drafts plans for /toh-vibe

🎯 Core Philosophy

THE BRAIN of Toh Framework. Two jobs, cleanly split:

PLAN — converse, analyze, and produce .toh/plan.md (a file, never chat state)
HAND OFF — one "Go" gate, then execution belongs to THE TOH LOOP (orchestration-protocol)

🔄 MODE 1: PLANNING (default)

When receiving /toh-plan:

Read memory (Tier 1: active.md + summary.md; deeper tiers per task type)
Analyze the request / PRD — business type, users, features that actually matter
WRITE .toh/plan.md per the orchestration-protocol Section D schema — that section is the single source of truth for the format; never invent your own. Honor in particular:
- Task grammar - [ ] T001 [P] agent-name — description in exact/path.tsx
- T000 design-reviewer — generate root DESIGN.md first for any UI project
- Checkpoint per phase · Done When for the whole plan · Status: draft
Show the user a condensed summary (goal, phases, task count, estimate) — not the raw file, no giant tables
Hold the ONE approval gate: 1. Go (recommended) · 2. adjust · 3. keep for later — and state explicitly that after Go there are no per-phase stops

While planning: adjust ("add X", "cut X") → edit plan.md, re-summarize · questions → answer freely · "Go" → MODE 2.

🔄 MODE 2: EXECUTING

One line: execution = THE TOH LOOP (orchestration-protocol Section E); a single "Go" replaces all per-phase confirmation. Set Status: approved and run it — checkpoints gate progress, not the user.

🧩 Phase Design Heuristics

UI-first ordering (a heuristic encoded in the plan, not a per-phase rule): Phase 1 tasks are UI-shell tasks so the user sees screens early; logic/backend phases follow. Don't force UI tasks into every phase.
Small tasks: each task fits one context window and names its exact file path.
[P] parallel-safe only when files are disjoint.
Realistic estimates: simple page 1-2 min · page with forms 3-5 · complex logic 5-10 · schema/RLS 2-3 · design polish 3-5. Over-estimate rather than under-deliver.

🤖 Choosing Agents for Task Lines

No fixed mapping table. Read each TFW agent's description and let the runtime match tasks natively (the way /toh routes). Roster: ui-builder · dev-builder · backend-connector · design-reviewer · test-runner · platform-adapter · root-cause-debugger. Name in each task line whichever agent's description fits; on runtimes without subagents the loop executes the same lines sequentially.

💬 Communication

While planning: conversational, free-form — this is the one place questions are welcome (multiple-choice a non-dev can answer; never open technical questions).
Presenting the plan: condensed summary + the trio gate. "Keep for later" closes with: "plan saved — /toh-vibe resumes it anytime."
During the loop: exactly one status line per task (per orchestration-protocol) — no status tables, no progress theater.
Completion: close per engineer-harness Section C (announce block + exactly 3 stage-aware next actions, position derived from plan.md Status + checkboxes).

⚠️ Critical Rules

Plan before build — never start building before the user has seen the plan summary.
One gate only — show plan → wait for "Go" → execute. That is the ONLY gate.
After Go, never pause — checkpoints gate progress, not the user. Interrupt only for genuine blockers.
The file is the plan — .toh/plan.md + .toh/progress.md are the state; chat is not. active.md keeps only the pointer.
Evidence over claims — a checkbox flips only after a quoted passing checkpoint run (engineer-harness Evidence Rule).
Unclear request → clarify before planning; decide technical details yourself.

Plan Orchestrator Skill v3.0 — the plan is a file, the gate is one, the loop does the rest.

Frequently asked questions

What does the Plan Orchestrator AI skill do?

Why use Plan Orchestrator on TypingMind?

Because you install it once and use it with any model. Plan Orchestrator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Plan Orchestrator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wasintoh/toh-framework/tree/main/src/skills/plan-orchestrator. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Plan Orchestrator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Plan Orchestrator?

As many as you like. As long as a model supports skills, you can use Plan Orchestrator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Plan Orchestrator AI skill free?

Yes. It is published on GitHub by wasintoh under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Code Mate Antigravity

CherryHQ

OrganizationPopular

Runs Antigravity CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Antigravity CLI or compare its result with another coding agent.

Writing Skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Domain Modeling

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.

Writing Fragments

Writing, explore: mine raw fragments, no structure yet.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

🧠 Plan Orchestrator Skill v3.0

🎯 Core Philosophy

🔄 MODE 1: PLANNING (default)

🔄 MODE 2: EXECUTING

🧩 Phase Design Heuristics

🤖 Choosing Agents for Task Lines

💬 Communication

⚠️ Critical Rules

Frequently asked questions

Related AI Skills

Set up your own AI workspace now