Run CocoAdversary challenge review against a target.
Scanned 9/5/2026
Install to Claude Code
npx -y skills add Snowflake-Labs/cocoplus --skill cocoadversary --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Cocoadversary?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/snowflake-labs-cocoadversary-47a5354d)More formats (shields.io, HTML) on the badges page.
---
name: "adversary-run"
description: "Run CocoAdversary challenge review against a target."
version: "2.0.1"
author: "CocoPlus"
tags:
- cocoplus
- cocoadversary
---
Your objective is to implement `$adversary run [--target <path|stage|plan>] [--security] [--complexity]`.
Run a read-only challenge pass that looks for incorrect assumptions, weak evidence, hidden dependencies, security risk, complexity debt, and lifecycle gate bypass. Write the report under `.cocoplus/adversary/reports/`.
## Anti-Rationalization
| Shortcut / Temptation | Why It Fails |
|-----------------------|--------------|
| Treat the skill as complete because the file exists | Skill contracts must describe observable behavior and verification, not just command names. |
| Skip artifact and safety checks for a small command | Small commands still mutate state or guide execution; preserve the same gates. |
## Exit Criteria
- [ ] Command behavior matches the owning feature contract.
- [ ] Required reads, writes, and user-visible outputs are described.
- [ ] Safety, governance, and artifact constraints are preserved.
- [ ] Missing state produces a clear, non-destructive result.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!