The Hit logo

The Hit

Community
kucherenko
the-hit

Use when the execution plan is approved and it is time for parallel execution — dispatches workers through crew leads to implement work packages with TDD enforcement, report collection, and escalation protocols

Overview

Publisherkucherenko
Repositorygangsta
Skill namethe-hit
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 Hit 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-hit
  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-hit .claude/skills/the-hit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable The Hit 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 Hit 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 Hit 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 Hit: Execution and Parallel Coding

Overview

Workers and Crew Leads implement the Work Packages defined in the Execution Plan. Crews work simultaneously on their assigned territories, providing Reports (status updates) to the Underboss.

Trigger

Invoked after the Don approves the Execution Plan (Resource Development complete).

Process

Step 1: Underboss Distributes Work Packages

For each territory, the Underboss sends the Crew Lead:

  • The territory definition
  • The assigned Work Packages (ordered by dependency)
  • The relevant Contract sections
  • The applicable Constitution rules

Step 2: Crew Leads Dispatch Workers

Each Crew Lead (invoke gangsta:the-capo) processes their Work Packages:

  1. For each independent Work Package, dispatch a Worker subagent with subagent_type: "soldier" (do NOT use "general" or "general-purpose" — these are not valid in a Gangsta Agents installation), providing:

    • The Work Package brief
    • The Contract clause being implemented
    • Applicable Negative Constraints
    • Territory conventions
    • Prevention reminder: Workers MUST NOT reproduce Gangsta-internal spec identifiers (FR-xxx, NFR-xxx, WP-xxx, where xxx is one or more digits) in source code, tests, comments, or documentation. This is prevention guidance, not a gate.
    • Technical-debt prevention brief (Laundering gate): Laundering will block the Heist on five technical-debt checks. Workers must build today to pass those checks tomorrow:
      1. Copy/paste: do not clone build_setup in 5+ lines across files. If two call sites share logic, extract a helper or parameterize the variation. The duplicate will be caught by jscpd (min-lines 5, min-tokens 35) in Laundering.
      2. Long files: target ≤ 300 source lines per file. Hard block at 500. If a Work Package forces a long file, the Contract must name it and the Don must pre-approve — otherwise split by responsibility.
      3. Test coverage: write tests for every new public function and every modified branch. Laundering compares against the pre-Heist coverage baseline; coverage on modified code may not drop. If the project has a coverage threshold in its config, the run must meet it.
      4. Clean architecture: imports flow downward through layers (domain → application → infrastructure → delivery); no business logic in controllers, route handlers, DB adapters, or network clients; one responsibility per file.
      5. Clean code: remove dead code before reporting; functions ≤ 50 lines (blank/comment excluded); nesting ≤ 4 levels via early returns; no magic numbers in production paths; identifiers must name themselves.
    • Worker Report must self-report against these five points. See Step 4.
  2. Workers work in parallel within their territory (up to the allocated Worker count)

Step 3: TDD Enforcement

Every Worker MUST follow gangsta:drill-tdd — the full Red-Green-Refactor cycle:

  1. Write failing test — Based on the acceptance criteria
  2. Run test — Verify it fails for the right reason
  3. Write minimal implementation — Just enough to pass the test
  4. Run test — Verify it passes
  5. Refactor against the technical-debt brief — during the Refactor phase, verify against the five Laundering-gate items: no copy/paste with existing code, file under the long-file threshold, tests cover the new code, imports flow downward, no dead code / long functions / deep nesting / magic numbers / unnamed identifiers. Laundering will block the Heist on any of these.
  6. Report — Return Report to Crew Lead

A Worker that writes implementation before tests has its Report REJECTED.

Step 4: Report Collection

Each Worker returns a Report:

markdown
## Report: <WP-ID>
**Status:** success | failure | blocked
**TDD Cycle:**
- Test written: YES/NO
- Test failed first: YES/NO
- Implementation written: YES/NO
- Test passes: YES/NO
**Changes:**
- <file path>: <created/modified>
**Technical-Debt Self-Check:**
- Copy/paste: NONE | <file pair + reason if duplicated>
- Long files (longest created/modified): <N> lines
- Test coverage: <new/modified public functions and branches covered — list any uncovered>
- Clean architecture: <layer of each modified file + direction of any new import>
- Clean code: <functions >50 lines? nesting >4? magic numbers? dead code? — list any>
**Test Output:**

Step 5: Crew Lead Reviews Reports

The Crew Lead reviews each Report (invoke gangsta:the-capo):

  • Acceptance criteria met?
  • TDD cycle followed?
  • Tests passing?
  • Convention compliance?
  • Technical-debt self-check present and plausible? A Worker that reports NONE for every box without justification is suspect — flag for audit. The self-check is the early-warning system; Laundering enforces the gate.

Accept, reject with feedback, or escalate.

Step 6: Status Rollup

Crew Leads report territory status to the Underboss. The Underboss synthesizes for the Don:

markdown
## Heist Progress: <Heist Name>

| Territory | Completed | In Progress | Failed | Budget Used |
|-----------|-----------|-------------|--------|-------------|
| Frontend  | 3/5       | 1           | 1      | 60%         |
| Backend   | 4/4       | 0           | 0      | 45%         |
| ...       |           |             |        |             |

**Overall:** <N>/<Total> Work Packages complete

Step 7: Escalation Handling

When a Worker fails:

  1. Crew Lead retries — Fresh Worker, same Work Package
  2. Crew Lead escalates to Underboss — If retry fails or Contract is ambiguous
  3. Underboss mini-Grilling — Single-pass: Devils-Advocate attacks the proposed fix, Don weighs in, Synthesizer produces revised Contract clause
  4. Underboss escalates to Don — If beyond operational scope

Step 8: Completion

When all Crew Leads report territory completion:

  1. Underboss verifies: all Work Packages accepted, all tests passing
  2. Write the final checkpoint (status: completed, next-action: Proceed to Laundering)
  3. Immediately invoke gangsta:laundering — do NOT ask the Don what to do next, do NOT pause, do NOT prompt for confirmation. (This auto-advance is an authorized exception — documented in using-gangsta at the "Never auto-advance" rule, and in the-sit-down.)

Checkpoint

Write checkpoint after each significant batch of Work Packages completes (not just at the end):

yaml
---
heist: <heist-name>
phase: the-hit
status: in-progress | completed
timestamp: <ISO 8601>
next-action: <Continue Hit | Proceed to Laundering (auto)>
completed-wps: [WP-001, WP-002, ...]
pending-wps: [WP-003, ...]
failed-wps: [WP-004, ...]
artifacts:
  - <list of modified/created files>
---

Omerta Compliance

  • Introduction Rule: Workers dispatched through Crew Leads, no direct Worker communication
  • Rule of Truth: Reports include actual test output, not claims
  • Rule of Budget: Token usage tracked per Worker dispatch
  • Spec is Law: Every implementation traces to a Contract clause via Work Package
  • Technical-Debt Brief: Every Worker dispatch includes the five-point Laundering-gate brief; every Report includes a Technical-Debt Self-Check
  • Rule of Availability: Checkpoint updated after each batch

Frequently asked questions

What does the The Hit AI skill do?

Use when the execution plan is approved and it is time for parallel execution — dispatches workers through crew leads to implement work packages with TDD enforcement, report collection, and escalation protocols

Why use The Hit on TypingMind?

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

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

Which AI models can use The Hit?

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 Hit?

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

Is the The Hit 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 👇