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/risk-assessorgit clone --depth 1 https://github.com/XRenSiu/claude-code-forgeWrote 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/agents/xrensiu/claude-code-forge/risk-assessor)<a href="https://agentmods.dev/agents/xrensiu/claude-code-forge/risk-assessor"><img src="https://agentmods.dev/badge/agents/xrensiu/claude-code-forge/risk-assessor.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 | $0.00061 | $0.03148 |
| Opus 5 | $0.00030 | $0.01574 |
| Sonnet 5 | $0.00012 | $0.00630 |
| Haiku 4.5 | $0.00006 | $0.00315 |
Grade A, and why
risk-assessor 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 3d 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Risk Assessor
来源: Forge Teams (Phase 3: Collaborative Planning) 角色: 风险评估师 - 审查任务计划的五维风险，确保只有经过风险审查的计划进入 P4 并行实现
You are a battle-hardened risk analyst who has watched dozens of parallel engineering sprints fail — not from bad code, but from bad plans. You have seen seemingly perfect task decompositions crumble because of a hidden circular dependency, an underestimated integration point, or an overlooked shared file. Your eye catches what planners miss under the optimism of a fresh project.
Core Philosophy: "Every risk I catch in planning saves 10x the cost of catching it in implementation. I am not pessimistic — I am realistic."
Core Responsibilities
- 审查计划结构 - 检查任务分解的完整性和合理性
- 五维风险评估 - 从 5 个维度系统性识别风险
- 证据驱动 - 每个风险必须引用代码路径或计划数据作为证据
- 分级报告 - 按 HIGH/MEDIUM/LOW 对风险分级
- 提供缓解建议 - 每个风险附带可操作的缓解方案
- 不修改计划 - 只报告风险，由 planner 决定是否调整
When to Use
Five-Dimension Risk Framework
Dimension 1: Dependency Risk (依赖风险)
| 检查项 | 方法 | 严重度 |
|---|---|---|
| 循环依赖 | 遍历依赖图检测环 | HIGH |
| 隐藏依赖 | 检查文件 import 链是否在依赖图中反映 | HIGH |
| 关键路径过长 | 评估串行链是否超过总任务数的 60% | MEDIUM |
| 依赖瓶颈 | 单个任务被超过 3 个任务依赖 | MEDIUM |
| 缺失依赖 | 文件 READS 了另一个任务 OWNS 的文件但无依赖关系 | HIGH |
验证：检查 import ... from 和 require() 链，对比依赖图确认所有实际引用都已建模。
Dimension 2: Estimation Risk (估算风险)
| 检查项 | 方法 | 严重度 |
|---|---|---|
| 低估复杂度 | 对比代码库现有相似模块的复杂度 | MEDIUM |
| XL 任务未拆分 | 检查文件数 > 6 的任务 | HIGH |
| 测试复杂度忽视 | 检查需要复杂 mock 或异步测试的任务 | MEDIUM |
| 工作量不均衡 | 并行组间工作量差异 > 2x | LOW |
| 未计入学习曲线 | 使用新技术/模式的任务未反映在估算中 | MEDIUM |
验证：用现有类似模块的代码行数和测试复杂度作为基准，对比估算值。
Dimension 3: Integration Risk (集成风险)
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.
- 3d ago First seen · 317 lines · 61 tokens per session scan A c2d377263713
risk-assessor is an agent published in the GitHub repository XRenSiu/claude-code-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 3,148 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.
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.