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.
npx skills add kucherenko/gangsta --skill omertagit clone --depth 1 https://github.com/kucherenko/gangstaWrote 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.
[](https://agentmods.dev/skills/kucherenko/gangsta/omerta)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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
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.
- 9d ago First seen · 103 lines · 43 tokens per session scan A af7d105205be
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.
Other skills, from other repositories
cocotrace
Build and query the SHA-256 requirements-to-implementation traceability graph across lifecycle artifacts.
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.
cocoplus-config
CocoPlus configuration SSOT — $cocoplus sync propagates cocoplus.toml into downstream artifacts; $cocoplus migrate-config converts legacy safety-config.json. Invoked via $cocoplus sync and $cocoplus migrate-config.
bloom-crystallize
CocoBloom crystallization — converts a successful ship execution trace into a reusable skill file. Requires recent successful $ship. Invoked via $bloom crystallize.
context-add
Guided wizard to capture or update organizational Snowflake/Cortex standards into .cocoplus/context/ .md. Presents a menu of 6 standard types, collects answers via multi-turn dialogue, and commits the file.
discuss-red-team
CocoDiscuss Red-Team Mode — adversarial devil's advocate session that challenges spec assumptions before $plan. Invoked via $discuss --red-team.