Exodus

Community

GadaaLabs

exodus

Use when you have a written implementation plan to execute in a completely fresh isolated session — no context inheritance, clean slate execution with review checkpoints

Overview

Publisher	GadaaLabs
Repository	`claude-code-on-steroids`
Skill name	`exodus`
Stars	67
Forks	10
Bundled files	Instructions only
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 GadaaLabs on GitHub. Read the source before you install it.

Installation

Install the Exodus 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/GadaaLabs/claude-code-on-steroids.git /tmp/claude-code-on-steroids
mkdir -p .claude/skills
cp -r /tmp/claude-code-on-steroids/skills/exodus .claude/skills/exodus

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

Use it in TypingMind

Enable Exodus 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 Exodus 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 Exodus 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.

Executing Plans (Isolated Session)

Overview

EXODUS — An exodus is a deliberate departure into clean, uncharted territory — leaving all baggage behind. When invoked: loads a written plan into a completely fresh session with zero context inherited from the current conversation, executes each task exactly as specified, stops on any blocker, and hands off to SEAL when done.

Core principle: Fresh session per plan. No context pollution. Stop when blocked — never guess.

Announce at start: "Running EXODUS to execute this plan in an isolated session."

EXODUS vs PHANTOM — Which to Use

Question	EXODUS	PHANTOM
Do you want zero session context?	Yes — required	No — same session
Do you need fastest iteration?	No	Yes
Do you have a complex plan needing full isolation?	Yes	No
Are tasks tightly sequential?	Yes	Works either way

Rule: Large plans where context pollution is a real risk → EXODUS. Faster iteration in-session → PHANTOM.

Note: EXODUS delivers the highest quality output when subagents are available (Claude Code, Codex). If your platform supports it, consider phantom as an alternative that keeps the human in the loop between tasks.

The Process

Step 1: Load and Review Plan

Read the plan file completely
Review critically — identify any gaps, contradictions, or unclear steps
If concerns exist: raise them before starting. Do not guess.
If plan is clear: create task list and proceed

Step 2: Set Up Isolated Workspace

REQUIRED: Run vault before touching any files.


Running VAULT to set up an isolated workspace.

Never start implementation on main or master without explicit user consent.

Step 3: Execute Tasks

For each task in order:

Mark as in_progress
Follow every step exactly as written — do not improvise
Run all verifications specified in the plan
Mark as completed

Do not batch tasks. Complete and verify one at a time.

Step 4: Complete the Branch

After all tasks are complete and verified:


Running SEAL to complete this branch.

REQUIRED: invoke seal — do not merge or push manually.

When to Stop Immediately

Stop and ask for help when:

A dependency is missing or unavailable
A test fails and you don't know why
An instruction is unclear or contradictory
A verification fails repeatedly (2+ times)
The plan has a gap that prevents starting a step

Never guess your way through a blocker. Stop, explain what's blocked, and wait for direction.

Red Flags

Never:

Begin on main/master without explicit user consent
Skip the VAULT workspace setup
Improvise when a step is unclear — stop and ask
Continue past a failing verification
Batch-implement multiple tasks without verifying each

Always:

Review the plan critically before starting
Set up the isolated workspace with VAULT first
Complete tasks one at a time with verification
Hand off to SEAL — never merge manually

Integration

Required skills:

vault — workspace isolation before any task starts
blueprint — creates the plan this skill executes
seal — branch completion after all tasks finish

Alternative:

phantom — same-session plan execution with subagent-per-task and two-stage review

Frequently asked questions

What does the Exodus AI skill do?

Use when you have a written implementation plan to execute in a completely fresh isolated session — no context inheritance, clean slate execution with review checkpoints

Why use Exodus on TypingMind?

Because you install it once and use it with any model. Exodus 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 Exodus in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/GadaaLabs/claude-code-on-steroids/tree/main/skills/exodus. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Exodus?

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 Exodus?

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

Is the Exodus AI skill free?

It is published on GitHub by GadaaLabs. Check the repository for licensing terms. 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

Executing Plans

obra

CommunityPopular

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Finishing A Development Branch

obra

CommunityPopular

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Receiving Code Review

obra

CommunityPopular

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative…

Requesting Code Review

obra

CommunityPopular

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Executing Plans (Isolated Session)

Overview

EXODUS vs PHANTOM — Which to Use

The Process

Step 1: Load and Review Plan

Step 2: Set Up Isolated Workspace

Step 3: Execute Tasks

Step 4: Complete the Branch

When to Stop Immediately

Red Flags

Integration

Frequently asked questions

Related AI Skills

Set up your own AI workspace now