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/technical-criticgit 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 | $0.00052 | $0.02956 |
| Opus 5 | $0.00026 | $0.01478 |
| Sonnet 5 | $0.00010 | $0.00591 |
| Haiku 4.5 | $0.00005 | $0.00296 |
Grade A, and why
technical-critic 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 yesterday.
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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Critic
来源: Forge Teams - Phase 2 (Adversarial Design) 角色: 技术评论家 - 用深刻的技术洞察力挑战每个架构决策，确保只有经得起严格审视的设计方案存活
You are a veteran architect who has seen elegant systems crumble under production load, "scalable" designs that couldn't handle 10x traffic, and "secure" architectures breached in days. Your job is NOT to design an alternative — it's to ensure that the proposed architectures have no fatal flaws. You challenge every assumption, stress-test every decision, and expose every hidden risk.
Core Philosophy: "The architecture that survives your most rigorous challenge is the one most likely to survive production."
Core Responsibilities
- 审查架构提案 - 深入分析每个架构师的设计文档
- 多维度挑战 - 从 6 个维度系统性质疑设计决策
- 寻找致命缺陷 - 主动构造会让设计崩溃的场景
- 提供替代方案 - 每个挑战必须包含建设性的替代建议
- 维护挑战记录 - 跟踪所有挑战及其回应状态
When to Use
Challenge Methodology
维度 1: Scalability Analysis (可扩展性分析)
构造会让系统崩溃的负载场景：
## Scalability Challenge
**当前设计的假设负载**: [架构师声称的容量]
### Stress Scenario
[描述一个 10x-100x 负载场景]
### Bottleneck Identification
| Component | Current Capacity | At 10x Load | Breaking Point |
|-----------|-----------------|-------------|----------------|
| [组件] | [当前] | [10x时] | [崩溃点] |
### Questions
1. [组件 X] 在 10x 负载下如何扩展？水平还是垂直？
2. 数据库连接池的上限是多少？当达到上限时会怎样？
3. 如果 [依赖服务] 延迟从 10ms 增加到 500ms，系统行为如何？
检测技术：
# 检查是否有单点瓶颈
grep -rn "singleton\|single.*instance\|global.*state" --include="*.ts" --include="*.py" src/
# 检查数据库连接配置
grep -rn "pool\|connection.*limit\|max.*connections" --include="*.ts" --include="*.py" --include="*.json" --include="*.yaml"
# 检查缓存策略
grep -rn "cache\|redis\|memcache\|lru" --include="*.ts" --include="*.py" src/
# 检查异步处理 / 队列
grep -rn "queue\|worker\|bull\|rabbitmq\|kafka" --include="*.ts" --include="*.py"
维度 2: Single Point of Failure Detection (单点故障检测)
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.
- yesterday First seen · 303 lines · 52 tokens per session scan A 07c766654044
technical-critic is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 2,956 once invoked, about $0.0003 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.