The Ledger logo

The Ledger

Community
kucherenko
the-ledger

Use when reading or writing institutional memory — insights from successful solutions, fails from historical mistakes, and the Project Constitution that accumulates commandments and negative constraints across heists

Overview

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

Use it in TypingMind

Enable The Ledger 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 Ledger 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 Ledger 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 Ledger: Institutional Memory of the Gangsta Agents Family

Overview

The Ledger is the Gangsta Agents Family's persistent memory. It stores successful reasoning pathways (Insights), documented failures (Fails), and accumulated governance rules (the Project Constitution). Every Heist reads from and writes to the Ledger.

Directory Structure

The Ledger lives in the target project, NOT in the gangsta package:

docs/gangsta/
├── constitution.md             # Project Constitution (living document)
├── insights/                   # Repository of Insights (Good Catches)
│   └── YYYY-MM-DD-<topic>.md
└── fails/                      # Repository of Fails (Concrete Shoes)
    └── YYYY-MM-DD-<topic>.md

Initializing the Ledger

If docs/gangsta/ does not exist in the target project, create it:

bash
mkdir -p docs/gangsta/insights docs/gangsta/fails

Create an initial docs/gangsta/constitution.md:

markdown
# Project Constitution

## Commandments (from Insights)
_No commandments yet. They will be added as Heists produce insights._

## Negative Constraints (from Fails)
_No constraints yet. They will be added as Heists document failures._

## Architectural Decisions
_No decisions recorded yet._

Writing an Insight

Criteria: Record when a solution bypasses a complex constraint, discovers a non-obvious approach, or establishes a new Project Commandment.

File: docs/gangsta/insights/YYYY-MM-DD-<topic-slug>.md

markdown
---
date: YYYY-MM-DD
heist: <heist-name>
phase: <phase-where-discovered>
tags: [tag1, tag2, tag3]
---

# <Title: Short description of the insight>

## Discovery
<How the insight was found — which phase, what triggered it>

## Solution
<The successful reasoning pathway or creative solution>

## Project Commandment
<If applicable: a new rule to add to the Constitution>
<If not applicable: omit this section>

After writing, update docs/gangsta/constitution.md:

  • Add the commandment (if any) to the "Commandments" section
  • Include source reference: — Source: insights/YYYY-MM-DD-<topic>.md

Writing a Fail

Criteria: Record when an approach caused regressions, security gaps, wasted time, or led to incorrect implementation.

File: docs/gangsta/fails/YYYY-MM-DD-<topic-slug>.md

markdown
---
date: YYYY-MM-DD
heist: <heist-name>
phase: <phase-where-occurred>
tags: [tag1, tag2, tag3]
severity: critical | high | medium | low
---

# <Title: Short description of the failure>

## What Happened
<Description of the failure and its observable impact>

## Cognitive Diagnosis
<Causal mechanism explaining WHY the failure occurred — not just what went wrong, but the reasoning error that led to it>

## Negative Constraint
<The explicit prohibition: "NEVER [prohibited pattern] because [reason]">

After writing, update docs/gangsta/constitution.md:

  • Add the negative constraint to the "Negative Constraints" section
  • Include source reference: — Source: fails/YYYY-MM-DD-<topic>.md

Reading the Ledger

During Reconnaissance

Search insights/ and fails/ for entries with tags matching the current Heist topic. Present relevant entries in the Reconnaissance Dossier.

During The Grilling

The Devils-Advocate MUST check all Negative Constraints before accepting any proposal. If a proposal violates a Negative Constraint, it is automatically rejected.

During The Sit-Down

The Underboss references Commandments when drafting the Contract. Every relevant Commandment must be cited in the Contract.

During The Hit

Workers check Negative Constraints before implementation. If a Work Package would violate a constraint, the Worker escalates to the Crew Lead.

During Laundering

New insights and fails from the Heist are written. The Constitution is updated.

Omerta Compliance

  • Rule of Truth: All Ledger entries cite specific phases, heists, and observable evidence
  • Rule of Availability: Ledger files are committed to git after every update
  • Spec is Law: Negative Constraints in the Constitution are binding on all future Heists

Frequently asked questions

What does the The Ledger AI skill do?

Use when reading or writing institutional memory — insights from successful solutions, fails from historical mistakes, and the Project Constitution that accumulates commandments and negative constraints across heists

Why use The Ledger on TypingMind?

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

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

Which AI models can use The Ledger?

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 Ledger?

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

Is the The Ledger 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 👇