multi-model-review-router
by LocoLoboZ
Orchestrate independent reviews, adversarial audits, and multimodal analysis via secondary models and external tools.
- Trigger an adversarial review of high-risk code affecting billing or secrets.
- Invoke a 'rescue' model after the primary agent fails a task twice.
- Route long-context repository scans to specialized 1M+ token models.
Secure checkout via Stripe
Included in download
- Trigger an adversarial review of high-risk code affecting billing or secrets.
- Invoke a 'rescue' model after the primary agent fails a task twice.
- terminal automation included
- Ready for including Claude Code
See it in action
A real example of what this skill takes in and produces.
Sample input
I have just produced a migration script that modifies the authentication token handling path. Before I mark it complete, route this for independent adversarial review and return a report of any issues found.
Sample output
The skill classifies the request as a risk-path review trigger, checks tool availability against the readiness checklist, confirms authorisation for external routing, invokes the configured reviewer with a structured prompt, and integrates the findings into a final adjudicated response. The output includes the route used, reason for routing, input scope reviewed, reviewer findings, the active agent's adjudication, confirmed issues, open risks, evidence references, and a route log entry covering input scope, tool used, sensitivity level, and output location.
Orchestrate independent reviews, adversarial audits, and multimodal analysis via secondary models and external tools.
Secure checkout via Stripe
Included in download
- Trigger an adversarial review of high-risk code affecting billing or secrets.
- Invoke a 'rescue' model after the primary agent fails a task twice.
- terminal automation included
- Ready for including Claude Code
- Instant install
See it in action
A real example of what this skill takes in and produces.
Sample input
I have just produced a migration script that modifies the authentication token handling path. Before I mark it complete, route this for independent adversarial review and return a report of any issues found.
Sample output
The skill classifies the request as a risk-path review trigger, checks tool availability against the readiness checklist, confirms authorisation for external routing, invokes the configured reviewer with a structured prompt, and integrates the findings into a final adjudicated response. The output includes the route used, reason for routing, input scope reviewed, reviewer findings, the active agent's adjudication, confirmed issues, open risks, evidence references, and a route log entry covering input scope, tool used, sensitivity level, and output location.
About This Skill
What it does
The Multi-Model Review Router is a sophisticated orchestration layer that enables your AI agent to delegate specialized tasks to external models and tools. It acts as a safety-first "dispatcher" for high-stakes scenarios such as adversarial code reviews, multi-model consensus, and long-context repository analysis.
Why use this skill
Prompting an AI yourself often leads to "hallucination loops" where the agent validates its own mistakes. This skill breaks that cycle by enforcing independent verification. It provides a structured framework for:
- Adversarial Validation: Explicitly seeking flaws in a proposed plan or code change.
- Rescue Operations: Automatically triggering a second opinion after repeated task failures.
- Specialized Routing: Sending video, audio, or massive repositories to the specific models (like Gemini or local LLMs) best equipped to handle them.
Supported Scenarios
The skill is designed to integrate with external tools in your environment, including CLI-based reviewers, MCP servers, and secondary APIs. It produces an adjudicated report that combines raw findings from external tools with a final decision-making summary.
Use Cases
- Trigger an adversarial review of high-risk code affecting billing or secrets.
- Invoke a 'rescue' model after the primary agent fails a task twice.
- Route long-context repository scans to specialized 1M+ token models.
- Adjudicate conflicting opinions from multiple models into a final plan.
- Perform timestamped analysis of video or audio assets for technical audits.
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/multi-model-review-router | tar xz -C ~/.claude/skills/Free skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Early access skill
Be the first to review this skill.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
File Scopes
Tags
Works with any agent that supports the Universal SKILL.md standard, including Claude Code, Codex CLI, Cursor, VS Code Copilot, Gemini CLI, and any agent that supports the Universal SKILL.md standard. External reviewer tools must be separately configured in the buyer's environment.
Creator
I design and publish skills built from real professional practice across three areas: cyber security consulting, business operations, and AI workflow engineering. My cyber security skills draw on active advisory work spanning governance, risk, compliance, assurance, and executive reporting. They are built for practitioners who need structured, defensible outputs - not generic templates. My business operations skills cover the day-to-day work of running a consulting practice: bookkeeping, financial tracking, expense reconciliation, and marketing content - designed to reduce repetitive overhead and keep outputs consistent. My AI platform and workflow skills are built for people who want to get more out of Claude and similar platforms - covering prompt engineering, skill architecture, automation pipelines, and agent enhancement. Every skill I publish has been tested in production use before it reaches the marketplace. If it is here, it works.
Frequently Asked Questions
Learn More About AI Agent Skills
More Premium Skills
Bounty Security Pattern Master Library — 399 Vulnerability Patterns
A premium library of 399 vulnerability patterns and DeFi attack vectors for AI-driven bug hunting and security audits.
subagent-orchestrator (Develop based on the Claude Code sourcemap)
Turn your AI agent into a coordinator that manages parallel subagents for complex coding and research tasks.
software-architect
A structured framework for planning, reviewing, and evolving complex software systems with explicit trade-offs.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.