omerta

omerta is a skill for Claude Code from kucherenko/gangsta. It costs 43 tokens per session (979 once invoked), scanned A, original, MIT.

A governance rulebook for a group of coding agents. It defines how agents communicate, how work is saved for recovery, and how authorization, accuracy, and resources are controlled.

In plain words
What is it for?
Enforcing communication boundaries, recording checkpoints, preserving session state, checking authority, avoiding invented information, and managing shared resources.
Why use it?
It keeps multi-agent work traceable and prevents unauthorized coordination, lost progress, and unsupported claims.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the gangsta plugin — 19 skills, 6 agents, 1 hook shipped together

Good fit Enforcing communication boundaries, recording checkpoints, preserving session state, checking authority, avoiding invented information, and managing shared resources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kucherenko/gangsta/omerta
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add kucherenko/gangsta --skill omerta
Clone the repo
git clone --depth 1 https://github.com/kucherenko/gangsta

Made for: Claude Code.

Or install gangsta, the plugin that ships this one along with the rest of its 19 skills, 6 agents, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for omerta

README.md
[![agentmods](https://agentmods.dev/badge/skills/kucherenko/gangsta/omerta/github.svg)](https://agentmods.dev/skills/kucherenko/gangsta/omerta)
Your own site
<a href="https://agentmods.dev/skills/kucherenko/gangsta/omerta"><img src="https://agentmods.dev/badge/skills/kucherenko/gangsta/omerta/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for omerta

Your own site · 80×15
<a href="https://agentmods.dev/skills/kucherenko/gangsta/omerta"><img src="https://agentmods.dev/badge/skills/kucherenko/gangsta/omerta.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 979 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00979
Opus 5 $0.00022 $0.00490
Sonnet 5 $0.00009 $0.00196
Haiku 4.5 $0.00004 $0.00098

Measured 9d ago against content hash af7d105205be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

omerta scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/omerta/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Omerta: The Laws of the Gangsta Agents Family

Overview

Omerta is the governance framework for the Gangsta Agents Family. It is not a phase — it is a cross-cutting concern enforced by every skill at every stage. These laws are non-negotiable.

The Five Laws

Law 1: The Introduction Rule (Authorization Protocol)

No agent-to-agent interaction occurs without mediation by the Underboss or Don.

  • Workers CANNOT communicate directly with each other
  • All messages pass through the chain: Worker → Crew Lead → Underboss
  • This prevents "shadow coordination" where agents develop shared assumptions outside the spec
  • Violation: Any attempt at direct agent-to-agent messaging is blocked and logged

Law 2: The Rule of Availability (State Durability)

All Heist state MUST be checkpointed to files. If a session is interrupted, state must be recoverable.

  • Checkpoint location: docs/gangsta/<heist-name>/checkpoints/YYYY-MM-DD-checkpoint-<phase>.md
  • Checkpoint format: YAML frontmatter with phase, status, timestamp, resume instructions
  • Every phase transition writes a checkpoint BEFORE starting the next phase
  • On session resume, the Don reads the latest checkpoint and continues from that point

Checkpoint template:

---
heist: <heist-name>
phase: <current-phase>
status: in-progress | completed | blocked
timestamp: YYYY-MM-DDTHH:MM:SS
next-action: <what to do next>
artifacts:
  - <list of files produced so far>
---

## Resume Context
<Summary of what has been done and what remains>

Law 3: The Rule of Truth (Anti-Hallucination)

Every claim MUST cite its source. Agents adopt a "Fact-First" posture.

Claim Type Required Citation
Code behavior file:line reference
Spec requirement Contract section name
Architectural decision Constitution entry
Past pattern Ledger insight/fail reference
  • Any uncited claim is invalid and must be flagged immediately
  • The Consigliere has standing authority to invoke a Truth check at any point
  • When flagged, the agent must either provide a citation or retract the claim

Read the full file on GitHub · 103 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 103 lines · 43 tokens per session scan A af7d105205be

Subscribe to this mod's changes

omerta is a skill published in the GitHub repository kucherenko/gangsta (81 stars, last pushed 25d ago), licensed MIT. It adds 43 tokens to every session and 979 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.