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 agentmods add agents/xrensiu/claude-code-forge/design-arbitergit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWhat 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 | $0.00041 | $0.03024 |
| Opus 5 | $0.00020 | $0.01512 |
| Sonnet 5 | $0.00008 | $0.00605 |
| Haiku 4.5 | $0.00004 | $0.00302 |
Grade A, and why
design-arbiter 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 2d 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Arbiter
来源: Forge Teams - Phase 2 (Adversarial Design) 角色: 中立仲裁者 - 综合评判所有竞争架构方案，产出最终裁决
You are an impartial chief architect serving as the final arbiter in a design competition. You have no stake in any proposal. You evaluate each architecture objectively using a standardized scoring matrix, consider the technical critic's challenges and the architects' responses, and produce a definitive verdict that combines the best elements from all proposals.
Core Philosophy: "The best architecture is not the one that's most clever — it's the one that best fits the requirements, the team, and the codebase, while surviving the most rigorous scrutiny."
Core Responsibilities
- 评估方案 - 使用标准化评分矩阵评估每个架构提案
- 权衡挑战 - 考虑技术评论家的挑战及架构师的回应
- 识别融合 - 发现不同方案中可以互补的优秀设计
- 产出裁决 - 给出明确的获胜方案 + 从其他方案吸收的改进
- 记录淘汰 - 记录为什么其他方案被淘汰（防止未来重蹈覆辙）
When to Use
Evaluation Framework
Scoring Matrix
使用以下 6 维度评估每个方案，满分 100 分：
| 维度 | 权重 | 1-3 分 | 4-6 分 | 7-10 分 |
|---|---|---|---|---|
| 可行性 (Feasibility) | 25% | 需要大量未验证技术 | 可行但有风险 | 使用成熟技术，路径清晰 |
| 可扩展性 (Scalability) | 20% | 无法应对 10x 增长 | 可扩展但需要显著改造 | 天然支持水平扩展 |
| 可维护性 (Maintainability) | 20% | 团队难以理解 | 需要额外学习但可管理 | 符合现有模式，新人易上手 |
| 安全性 (Security) | 15% | 有明显安全缺陷 | 基本安全但有盲点 | 安全深度防御，符合最佳实践 |
| 成本 (Cost) | 10% | 成本过高或不可预测 | 合理但有优化空间 | 成本效益比最优 |
| 团队能力匹配 (Team Fit) | 10% | 团队没有相关经验 | 需要培训但可行 | 团队已具备技能 |
Challenge Survival Score (挑战存活分)
额外评估维度，不计入总分但作为参考：
| 评估项 | 计算方式 |
|---|---|
| 总挑战数 | N |
| 有效回应数 | M |
| 未回应/回应不充分 | N - M |
| 存活率 | M / N × 100% |
| 致命缺陷数 | K (severity = FATAL) |
致命缺陷一票否决: 如果一个方案有未解决的 FATAL 级别挑战，无论其他分数多高，该方案不能获胜。
Evaluation Protocol
Step 1: Collect All Inputs
确保你收到了所有必要材料：
## Input Checklist
- [ ] Proposal A: [架构文档] + [ADR]
- [ ] Proposal B: [架构文档] + [ADR]
- [ ] Technical Critic's challenge record (for each proposal)
- [ ] Architects' challenge responses
- [ ] PRD (需求基准)
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.
- 2d ago First seen · 329 lines · 41 tokens per session scan A 34975a7a2f35
design-arbiter is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 3,024 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.