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.
git clone --depth 1 https://github.com/HermeticOrmus/claude-code-game-developmentWrote 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/commands/hermeticormus/claude-code-game-development/multi-agent-review)<a href="https://agentmods.dev/commands/hermeticormus/claude-code-game-development/multi-agent-review"><img src="https://agentmods.dev/badge/commands/hermeticormus/claude-code-game-development/multi-agent-review.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.01230 |
| Opus 5 | $0.00000 | $0.00615 |
| Sonnet 5 | $0.00000 | $0.00246 |
| Haiku 4.5 | $0.00000 | $0.00123 |
Grade A, and why
multi-agent-review 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 5d 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.
This is a copy
100% identical to multi-agent-review — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Code Review Orchestration Tool
Role: Expert Multi-Agent Review Orchestration Specialist
A sophisticated AI-powered code review system designed to provide comprehensive, multi-perspective analysis of software artifacts through intelligent agent coordination and specialized domain expertise.
Context and Purpose
The Multi-Agent Review Tool leverages a distributed, specialized agent network to perform holistic code assessments that transcend traditional single-perspective review approaches. By coordinating agents with distinct expertise, we generate a comprehensive evaluation that captures nuanced insights across multiple critical dimensions:
- Depth: Specialized agents dive deep into specific domains
- Breadth: Parallel processing enables comprehensive coverage
- Intelligence: Context-aware routing and intelligent synthesis
- Adaptability: Dynamic agent selection based on code characteristics
Tool Arguments and Configuration
Input Parameters
$ARGUMENTS: Target code/project for review- Supports: File paths, Git repositories, code snippets
- Handles multiple input formats
- Enables context extraction and agent routing
Agent Types
- Code Quality Reviewers
- Security Auditors
- Architecture Specialists
- Performance Analysts
- Compliance Validators
- Best Practices Experts
Multi-Agent Coordination Strategy
1. Agent Selection and Routing Logic
- Dynamic Agent Matching:
- Analyze input characteristics
- Select most appropriate agent types
- Configure specialized sub-agents dynamically
- Expertise Routing:
def route_agents(code_context): agents = [] if is_web_application(code_context): agents.extend([ "security-auditor", "web-architecture-reviewer" ]) if is_performance_critical(code_context): agents.append("performance-analyst") return agents
2. Context Management and State Passing
- Contextual Intelligence:
- Maintain shared context across agent interactions
- Pass refined insights between agents
- Support incremental review refinement
- Context Propagation Model:
class ReviewContext: def __init__(self, target, metadata): self.target = target self.metadata = metadata self.agent_insights = {} def update_insights(self, agent_type, insights): self.agent_insights[agent_type] = insights
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.
- 5d ago First seen · 194 lines · 0 tokens per session scan A bf33bcd91fb4
multi-agent-review is a command published in the GitHub repository HermeticOrmus/claude-code-game-development (62 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,230 tokens. A static security scan graded it A with 0 findings. It is 100% identical to multi-agent-review, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
announce
Draft X/Twitter announcement post (or thread) for the latest plugin release.
check-architecture
Angular Architecture Review.
ia-agent-native-audit
Score each of the 5 agent-native principles (parity, granularity, composability, emergent capability, improvement-over-time) against a codebase and report gaps.
audio-pass
Functional audio review for implementation, mix coverage, clarity, and player feedback.
cert-check
Review the current state against certification and platform compliance expectations.
sm-buff
You usually don't run buff directly — run sm sail. sm sail drives the whole PR to green and calls buff watch / triage for you, stopping only when it needs you to act (see /sm-sail). Reach for sm buff here only for surgical work: inspecting a specific failure, or resolving a single review thread when sail has parked on…