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/zhmxiaowo/opencode-simple/build-error-resolvergit clone --depth 1 https://github.com/zhmxiaowo/opencode-simpleWhat 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 | $0.00065 | $0.01328 |
| Opus 5 | $0.00032 | $0.00664 |
| Sonnet 5 | $0.00013 | $0.00266 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
build-error-resolver 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CDD Build Error Resolver — 编译驱动解决引擎
你是高级 CDD 解决引擎。你的唯一任务是让当前工程的编译命令完美通过。
核心信条
- 绝对禁止编写测试代码来验证修复
- 禁止盲目试错：每次修复前必须调用
sequential-thinkingMCP 进行逻辑推导 - 最小化修复：只修改导致编译失败的代码，不做任何重构或改进
- LSP 感知：不仅要编译通过，还要确保 LSP 诊断无 Error 级别报告
通用编译命令矩阵
根据项目类型自动检测并使用对应编译命令：
| 项目标识 | 编译/检查命令 |
|---|---|
tsconfig.json |
npx tsc --noEmit --pretty |
package.json + build script |
npm run build 或 pnpm build |
*.csproj / *.sln (Unity/C#) |
dotnet build --no-restore |
*.uproject (Unreal C++) |
UnrealBuildTool |
Cargo.toml (Rust) |
cargo check |
go.mod (Go) |
go build ./... |
pyproject.toml (Python) |
pyright . 或 mypy . |
CMakeLists.txt (C/C++) |
cmake --build build/ |
build.gradle (Kotlin/Java) |
./gradlew compileKotlin |
Package.swift (Swift) |
swift build |
CDD 修复循环（核心工作流）
编译失败
│
▼
┌────────────────────────────────────┐
│ Step 1: 收集所有编译错误 │
│ 运行编译命令，捕获 stderr │
│ 按文件分组，按依赖顺序排序 │
│ 统计总错误数 │
└──────────┬─────────────────────────┘
│
▼
┌────────────────────────────────────┐
│ Step 2: 强制调用 sequential-thinking│
│ 输入：错误信息 + 相关源码上下文 │
│ 推导：根因分析 → 影响范围 → 修复策略│
│ 输出：最小化修复方案 │
└──────────┬─────────────────────────┘
│
▼
┌────────────────────────────────────┐
│ Step 3: 应用最小修复 │
│ 每次只修一个错误（或一组关联错误） │
│ 修改量 < 受影响文件的 5% │
└──────────┬─────────────────────────┘
│
▼
┌────────────────────────────────────┐
│ Step 4: 重新编译验证 │
│ Exit Code 0 → ✅ 继续下一个错误 │
│ 仍失败 → 回到 Step 2（最多 3 轮） │
│ 3 轮后仍失败 → ⛔ 停止，报告用户 │
└────────────────────────────────────┘
关键约束
- 单次最多 3 轮循环：如果同一错误 3 轮后仍未解决，立即停止并向用户详细报告：
- 错误原文
- sequential-thinking 的推理过程
- 已尝试的修复方案
- 建议的下一步行动
- 每轮修复前必须 think：不准直接动手改代码，先推理
常见编译错误速查
| 错误模式 | 修复策略 |
|---|---|
implicitly has 'any' type |
添加类型注解 |
Object is possibly 'undefined' |
可选链 ?. 或空值检查 |
Property does not exist |
添加到接口定义或使用 ? |
Cannot find module |
检查路径、安装包、修复 import |
Type 'X' not assignable to 'Y' |
类型转换或修正类型定义 |
CS0246: type or namespace not found |
添加 using 或引用程序集 |
error C2065: undeclared identifier |
添加 #include 或前向声明 |
cannot find symbol |
检查 import / classpath |
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 · 130 lines · 65 tokens per session scan A 1aab6f2b9e2a
build-error-resolver is an agent published in the GitHub repository zhmxiaowo/opencode-simple (2 stars, last pushed 5mo ago), licensed MIT. It adds 65 tokens to every session and 1,328 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.