
omerta
Use when enforcing governance guardrails during any gangsta operation — referenced as cross-cutting concern by all skills for anti-hallucination, authorization, state durability, resource management, and spec supremacy rules
- Installs
- 43
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/kucherenko/gangsta --skill omerta- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads omerta automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
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
Law 4: The Rule of Budget (Resource Management)
- Each Crew Lead operates within an allocated token budget set by the Underboss
- Workers report resource consumption in their Reports
- If a territory exceeds its budget, work pauses until the Underboss approves additional allocation
- All "profits" (merged code, passing tests) are reported up: Worker → Crew Lead → Underboss → Don
Law 5: The Spec is Law
The specification is the absolute source of truth.
- If code contradicts the spec, the SPEC is revised first — never the reverse
- No "shadow code" hotfixes — every code change must trace to a Contract clause
- If a bug is found during The Hit:
- Worker escalates to Crew Lead
- Crew Lead escalates to Underboss
- Underboss may invoke a mini-Grilling (single-pass) to revise the Contract
- Only after Contract revision does implementation proceed
Omerta Compliance Checklist
Every skill MUST verify this checklist before proceeding to the next phase or action:
- Introduction Rule: All agent interactions mediated by hierarchy (no direct Worker-to-Worker)
- Rule of Availability: Current state checkpointed to file
- Rule of Truth: All claims cite their source (no invalid claims)
- Rule of Budget: Resource consumption within allocated budget
- Spec is Law: All changes trace to a Contract clause
Red Flags
If you catch yourself thinking any of these, STOP — you are about to violate Omerta:
| Thought | Violated Law |
|---|---|
| "I'll just make this quick fix without updating the spec" | Law 5: Spec is Law |
| "I know this is true, I don't need to cite it" | Law 3: Rule of Truth |
| "Let me ask that other agent directly, it's faster" | Law 1: Introduction Rule |
| "I'll save the checkpoint after I finish this part" | Law 2: Rule of Availability |
| "We're close to done, the budget doesn't matter now" | Law 4: Rule of Budget |
FAQ
What does the omerta skill do?
Use when enforcing governance guardrails during any gangsta operation — referenced as cross-cutting concern by all skills for anti-hallucination, authorization, state durability, resource management, and spec supremacy rules
How do I install omerta?
Run npx skills add https://github.com/kucherenko/gangsta --skill omerta in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/omerta/ (personal) or .claude/skills/omerta/ (project).
Which AI agents can use omerta?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is omerta safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains omerta?
It is published by kucherenko in kucherenko/gangsta. It has 43 recorded installs.
More from kucherenko/gangsta
audit-review
kucherenko/gangsta
Open the skill to read its SKILL.md instructions.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.