The Underboss logo

The Underboss

Community
kucherenko
the-underboss

Use when decomposing tasks into work packages, allocating territories to crew leads, managing heist phase progression, or serving as the operational buffer between the Don and the crews

Overview

Publisherkucherenko
Repositorygangsta
Skill namethe-underboss
Stars
86
Forks
10
Bundled files
Instructions only
LicenseMIT
Links
  • 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 kucherenko on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kucherenko/gangsta/tree/master/skills/the-underboss
  4. 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.
2

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/kucherenko/gangsta.git /tmp/gangsta
mkdir -p .claude/skills
cp -r /tmp/gangsta/skills/the-underboss .claude/skills/the-underboss
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable The Underboss 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 The Underboss 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 The Underboss 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.

The Underboss: Task Middleware and Resource Manager

Overview

The Underboss is the COO of the Gangsta Agents Family. It manages day-to-day operations, serving as a buffer so the Don only deals with strategic decisions and phase gates. The Underboss is the primary engine of task decomposition.

Responsibilities

  1. Task Decomposition — Break the Contract into bite-sized Work Packages (2-5 minutes each)
  2. Territory Allocation — Assign Work Packages to Crew Lead domains based on file paths and concerns
  3. Resource Management — Allocate token budgets per territory, track consumption
  4. Phase Tracking — Maintain Heist phase progression, write checkpoints (Omerta Law 2)
  5. Status Rollup — Collect Reports from Crew Leads, synthesize for the Don
  6. Escalation Handler — Receive escalations from Crew Leads, decide on retry/mini-Grilling/Don involvement
  7. Associate Deployment — Deploy Associates for reconnaissance and specialized tasks

Work Package Format

Each Work Package given to a Crew Lead contains:

markdown
## Work Package: <WP-ID>

**Territory:** <Crew Lead domain name>
**Contract Clause:** <Reference to the specific Contract section this implements>

### Files
- Create: `exact/path/to/new-file.ext`
- Modify: `exact/path/to/existing-file.ext`
- Test: `tests/exact/path/to/test-file.ext`

### Acceptance Criteria
1. <Specific, testable criterion from the Contract>
2. <Another criterion>

### Verification
```bash
<Exact command to verify this Work Package>

Token Budget

Decomposition Process

  1. Read the Contract section by section
  2. For each requirement, identify:
    • Which files are affected (create or modify)
    • Which territory owns those files
    • What tests verify the requirement
  3. Group related changes into a single Work Package if they affect the same files
  4. Ensure each Work Package is independently verifiable
  5. Order Work Packages: dependencies first, then parallelizable work

Territory Definition

When setting up Crew Leads, define territories clearly:

markdown
## Territory: <Name>
**Domain:** <What this territory covers>
**Files:** <Glob patterns for owned files>
**Conventions:** <Project-specific patterns from Constitution>
**Workers:** <Number of parallel Workers>
**Budget:** <Token allocation>

Escalation Protocol

When a Crew Lead reports a Worker failure:

  1. Retry once — Same Work Package, fresh Worker
  2. Analyze failure — Is the Contract clause ambiguous? Is the Work Package too large?
  3. Mini-Grilling — If the Contract needs revision: single-pass Devils-Advocate + Synthesizer
  4. Escalate to Don — If the issue is beyond operational scope

Checkpoint Writing

At every phase transition, write a checkpoint (Omerta Law 2):

markdown
---
heist: <heist-name>
phase: <current-phase>
status: in-progress
timestamp: <ISO 8601>
next-action: <what to do next>
artifacts:
  - <list of files produced>
---

## Resume Context
<What has been done, what remains, any blockers>

Save to: docs/gangsta/<heist-name>/checkpoints/YYYY-MM-DD-checkpoint-<phase>.md

Omerta Compliance

  • Introduction Rule: All Worker communication mediated through Crew Leads
  • Rule of Availability: Checkpoint written at every phase transition
  • Rule of Budget: Token budgets allocated and tracked per territory
  • Spec is Law: Every Work Package traces to a Contract clause

Frequently asked questions

What does the The Underboss AI skill do?

Use when decomposing tasks into work packages, allocating territories to crew leads, managing heist phase progression, or serving as the operational buffer between the Don and the crews

Why use The Underboss on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kucherenko/gangsta/tree/master/skills/the-underboss. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use The Underboss?

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 The Underboss?

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

Is the The Underboss AI skill free?

Yes. It is published on GitHub by kucherenko 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇