adversarial-code-review
Use when independently reviewing working-tree changes, staged changes, commits, or pull requests before merge, especially AI-generated code, large or…
Skill by leonardoacosta
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/leonardoacosta-adversarial-code-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/adversarial-code-review
What's inside
- Skill name
adversarial-code-review- Description
- Use when independently reviewing working-tree changes, staged changes, commits, or pull requests before merge, especially AI-generated code, large or cross-module changes, weak or rewritten tests, requirement drift, suspicious scope, unverifiable completion claims, or security, transaction, concurrency, performance, dependency, compatibility, and operational risks.
- License
- unknown
- Instructions
- 175 lines in SKILL.md · view on GitHub
Files (7)
- README.md
- SKILL.md
- openai.yaml · agents/
- README.zh-CN.md · docs/
- language-checks.md · references/
- review-domains.md · references/
- scope-and-test-integrity.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from leonardoacosta/agents
- 0.565score
agentmail
leonardoacosta
Build with the AgentMail TypeScript or Python SDK for inbox, message, thread, draft, attachment, domain, allow/block list, pod, webhook, and WebSocket…
SkillAFreshness: AClaude Code +9 - 0.559score
9router
leonardoacosta
Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch.
SkillAFreshness: AClaude Code +9 - 0.556score
agent-browser-policy
leonardoacosta
Apply consent, secret-safe authorized login, session ownership, profile, CDP, and harness-versus-CLI boundaries whenever agent-browser is used, including…
SkillAFreshness: AClaude Code +9 - 0.529score
ascii-wireframe
leonardoacosta
Author UI wireframes as Unicode box-drawing TEXT (┌─┐│└┘) that embeds directly into proposal.md, tasks.md, beads issues, and PR/issue bodies — the corpus's…
SkillBFreshness: BClaude Code +9 - 0.524score
agent-tooling
leonardoacosta
Choosing among agent tooling surfaces — when to add an MCP server vs use a CLI/WebFetch, when to render a diagram with Mermaid vs another approach, and when a…
SkillBFreshness: BClaude Code +9 - 0.524score
autoresearch-loop
leonardoacosta
Optimize one bounded instruction or reference atom against a frozen evaluation suite with an auditable KEEP/REVERT ratchet.
SkillBFreshness: BClaude Code +9 - 0.524score
agent-architecture
leonardoacosta
Design AI agent architectures with orchestrator patterns, agent composition, tool selection, context management, and multi-agent coordination.
SkillBFreshness: BClaude Code +9 - 0.521score
apply
leonardoacosta
Execute one approved feature or an ordered feature queue through implementation, verification, recovery, and truthful closeout while preserving repository…
SkillBFreshness: BClaude Code +9 - 0.520score
animejs
leonardoacosta
anime.js v4 usage patterns — imperative JS animation timelines, SVG line drawing, stagger grids, and text effects (scrambleText, splitText).
SkillBFreshness: BClaude Code +9 - 0.519score
app-service-worker-observability
leonardoacosta
Establish and review the Azure App Service observability baseline for .NET worker, WebJob, background-service, or ASP.NET Core deployments.
SkillBFreshness: BClaude Code +9 - 0.519score
agent-instruction-pairing
leonardoacosta
Set up and maintain paired CLAUDE.md and AGENTS.md files for cross-runner agent-instruction parity across repo roots and nested packages.
SkillBFreshness: BClaude Code +9 - 0.519score
adversarial
leonardoacosta
Routes adversarial engineering work to the right review or testing method.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 19, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/leonardoacosta/agents
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from leonardoacosta
- 0.565score
agentmail
leonardoacosta
Build with the AgentMail TypeScript or Python SDK for inbox, message, thread, draft, attachment, domain, allow/block list, pod, webhook, and WebSocket…
SkillAFreshness: AClaude Code +9 - 0.559score
9router
leonardoacosta
Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch.
SkillAFreshness: AClaude Code +9 - 0.556score
agent-browser-policy
leonardoacosta
Apply consent, secret-safe authorized login, session ownership, profile, CDP, and harness-versus-CLI boundaries whenever agent-browser is used, including…
SkillAFreshness: AClaude Code +9 - 0.529score
ascii-wireframe
leonardoacosta
Author UI wireframes as Unicode box-drawing TEXT (┌─┐│└┘) that embeds directly into proposal.md, tasks.md, beads issues, and PR/issue bodies — the corpus's…
SkillBFreshness: BClaude Code +9 - 0.524score
agent-architecture
leonardoacosta
Design AI agent architectures with orchestrator patterns, agent composition, tool selection, context management, and multi-agent coordination.
SkillBFreshness: BClaude Code +9 - 0.524score
autoresearch-loop
leonardoacosta
Optimize one bounded instruction or reference atom against a frozen evaluation suite with an auditable KEEP/REVERT ratchet.
SkillBFreshness: BClaude Code +9
Cite this page
adversarial-code-review skill. Agent Mart. https://agentmart.dev/skills/leonardoacosta-adversarial-code-review (last updated 2026-10-24)