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/cacr92/wereply/readmegit clone --depth 1 https://github.com/cacr92/WeReplyWrote 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/cacr92/wereply/readme)<a href="https://agentmods.dev/agents/cacr92/wereply/readme"><img src="https://agentmods.dev/badge/agents/cacr92/wereply/readme.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 | $0.00000 | $0.01724 |
| Opus 5 | $0.00000 | $0.00862 |
| Sonnet 5 | $0.00000 | $0.00345 |
| Haiku 4.5 | $0.00000 | $0.00172 |
Grade A, and why
README 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 4d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents 配置说明
本目录包含 CaCrFeedFormula 项目的专业 Agents（子代理）配置。
什么是 Agents？
Agents 是专门化的 AI 助手，每个 Agent 专注于特定的技术领域或任务类型。它们具有：
- 隔离的上下文窗口：每个 Agent 维护独立的记忆
- 领域特定智能：针对特定任务优化的指令
- 精细的工具权限：基于角色的工具访问控制
可用的 Agents
1. rust-backend-specialist
专长：Rust 后端开发 工具：Read, Write, Edit, Bash, Glob, Grep 适用场景：
- Tauri 命令开发
- SQLx 数据库访问
- 异步编程
- 性能优化
何时使用：
- 开发新的 Tauri 命令
- 优化数据库查询
- 实现异步业务逻辑
- 性能调优
2. react-frontend-specialist
专长：React TypeScript 前端开发 工具：Read, Write, Edit, Bash, Glob, Grep 适用场景：
- React 组件开发
- 状态管理（TanStack Query）
- Tauri 集成
- 性能优化
何时使用：
- 创建新组件
- 实现复杂交互
- 优化渲染性能
- 集成后端 API
3. formula-optimization-specialist
专长：饲料配方优化 工具：Read, Write, Edit, Bash, Glob, Grep 适用场景：
- 线性规划优化
- HiGHS 求解器
- 营养计算
- 预混料设计
何时使用：
- 实现配方优化算法
- 处理营养计算
- 设计预混料方案
- 优化求解性能
4. test-automation-specialist
专长：测试自动化 工具：Read, Write, Edit, Bash, Glob, Grep 适用场景：
- 单元测试
- 集成测试
- TDD 工作流
- 测试覆盖率
何时使用：
- 编写测试用例
- 实施 TDD
- 提高测试覆盖率
- Mock 和 Stub
5. security-auditor
专长：安全审计 工具：Read, Grep, Glob（只读） 适用场景：
- 代码安全审查
- 漏洞检测
- 依赖安全
- 合规性检查
何时使用：
- 代码审查
- 安全审计
- 漏洞扫描
- 依赖检查
使用方式
方法 1：通过 Task 工具调用
// 在对话中使用
"请使用 rust-backend-specialist agent 帮我优化这个数据库查询"
方法 2：项目级配置
将 agent 文件放在 .claude/agents/ 目录中，Claude Code 会自动识别。
方法 3：全局配置
将 agent 文件放在 ~/.claude/agents/ 目录中，所有项目都可使用。
Agent 配置结构
每个 Agent 文件遵循以下结构：
---
name: agent-name
description: Agent 的用途和适用场景
tools: Read, Write, Edit, Bash, Glob, Grep
---
# Agent 标题
## 核心职责
- 职责 1
- 职责 2
## 技术规范
- 代码模板
- 最佳实践
## 开发检查清单
- [ ] 检查项 1
- [ ] 检查项 2
## 通信协议
- 与其他角色的协作方式
## 开发工作流
- 阶段 1
- 阶段 2
## 相关规范
- 相关的规范文件
## 相关 Skills
- 相关的 Skills
工具权限说明
Read, Grep, Glob（只读）
- 适用：审查类 Agent（security-auditor, code-reviewer）
- 权限：只能读取和搜索代码，不能修改
Read, Write, Edit, Bash, Glob, Grep（完整权限）
- 适用：开发类 Agent（rust-backend-specialist, react-frontend-specialist）
- 权限：可以读取、修改代码和执行命令
Read, Write, Edit, Glob, Grep（无 Bash）
- 适用：文档类 Agent
- 权限：可以读写文件，但不能执行命令
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.
- 4d ago First seen · 243 lines · 0 tokens per session scan A 019fcd170b5d
README is an agent published in the GitHub repository cacr92/WeReply (6 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,724 tokens. 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.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.