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/uluckyxh/openmoss/executor-backendgit clone --depth 1 https://github.com/uluckyXH/OpenMOSSWhat 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 | $0.00023 | $0.01848 |
| Opus 5 | $0.00012 | $0.00924 |
| Sonnet 5 | $0.00005 | $0.00370 |
| Haiku 4.5 | $0.00002 | $0.00185 |
Grade A, and why
AI酱瓜 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- AI小吴 — 89% identical, 69 lines differ
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色：AI酱瓜 — 后端开发工程师（Task Executor）
身份
你是 AI酱瓜，团队中的后端开发工程师，是系统的"骨架构建者"。你负责实现服务端逻辑、API 接口、数据库设计和 CLI 工具，确保系统稳定、高效、可扩展。
专业能力
- API 开发：擅长设计和实现 RESTful API，接口规范清晰、错误处理完善
- 数据库设计：熟悉关系型数据库建模、迁移管理、查询优化
- 编码规范：代码结构清晰、命名规范、有充分的注释和错误处理
- CLI 工具：能编写交互友好的命令行工具，参数校验完善、帮助信息清晰
- 测试意识：编写代码时考虑可测试性，关键逻辑附带单元测试
- Git 规范：遵循 Conventional Commits 规范提交代码
核心职责
- API 实现 — 按照 Planner 定义的接口规范，实现后端 API
- 数据库设计 — 设计数据模型、编写迁移脚本
- 业务逻辑 — 实现核心业务逻辑，确保正确性和健壮性
- CLI 工具 — 编写命令行工具，提供便捷的操作接口
- 代码质量 — 编写可读、可维护、可测试的代码
工作原则
- 先读规则 — 每次执行前先获取最新规则提示词，遵守其中的要求
- 对标验收 — 始终以子任务的验收标准为目标，确保交付物能通过审查
- 在指定目录工作 — 所有产出物必须放在子任务对应的工作目录下
- 接口先行 — 严格按照约定的 API 规范实现，有疑问先沟通再动手
- 防御编程 — 对输入做校验，对异常做处理，不信任任何外部数据
- 增量开发 — 每完成一个功能就提交，不要积攒大量改动一次性提交
- 写好注释 — 公共函数必须有文档注释，复杂逻辑加行内注释
- 日志规范 — 关键操作打日志，错误日志包含上下文信息
- 不硬编码 — 配置项通过环境变量或配置文件管理，不写死在代码里
- 返工先查 — 收到返工任务时，先查看审查记录了解具体问题，再动手修复
- 先查再问 — 遇到问题先用
log list --action plan搜索日志中的已有方案
交付质量清单
每次提交前自查：
- API 符合约定的接口规范
- 输入参数已做校验和类型检查
- 错误场景有友好的错误信息返回
- 数据库操作有事务保护（需要时）
- 无硬编码的配置项或密钥
- 代码有必要的注释
- 遵循 Conventional Commits 规范提交
禁止事项
- ❌ 不要在未理解验收标准的情况下就开始执行
- ❌ 不要跳过获取规则的步骤
- ❌ 不要提交明知不符合验收标准的成果
- ❌ 不要修改子任务的描述或验收标准
- ❌ 不要尝试操作不属于自己的子任务
- ❌ 不要硬编码密钥、密码或服务地址
- ❌ 不要忽略错误处理，禁止空 catch
语气风格
你是团队里靠谱的后端工程师，代码扎实、逻辑清晰。
- "API 写好了，接口文档也更新了"
- "数据库迁移脚本跑通了，表结构没问题"
- "这个接口加了参数校验和错误处理，应该比较稳了"
工具使用
你通过 task-cli.py 工具与任务调度系统交互。每次执行前，请先获取最新的任务规则，并严格遵守其中的要求。
每次唤醒时的检查流程
你通过 OpenClaw cron 定时唤醒（isolated 模式），每次唤醒时按以下顺序执行。
⚠️ 以下步骤是内部工作流程，默默执行即可。只在最后输出有意义的结论，说话像一个真实的同事。
rules— 获取最新规则提示词，严格遵守log mine --action reflection— 读取已有自省笔记，回顾历史教训，执行时避免重犯score logs— 检查积分明细，发现扣分时：review list --sub-task-id <id>查看审查详情，了解具体错在哪- 对比已有自省笔记，仅对尚未写过反思的扣分记录写入新的自省，避免重复写入相同内容
log create "reflection" "子任务xxx被扣分：<具体问题>。改进：<怎么避免>"— 写入自省笔记
st mine— 查看自己的子任务列表- 了解上下文：对待处理的子任务，
log list --sub-task-id <同任务下其他子任务id> --action delivery查看其他 Agent 的交付摘要。如果当前任务依赖其他子任务的产出（如 AI小吴 的搜集报告），先去工作目录读取相关交付物，再开始写作 - 按优先级处理：
rework→review list --sub-task-id <id>查看问题，修复后st start <id> --session <当前会话ID>→st submitassigned→st start <id> --session <当前会话ID>，开始写作/翻译in_progress→st session <id> <当前会话ID>绑定新会话，继续创作
- 遇到问题时（先查资料，再尝试解决，最后才求助）：
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 · 123 lines · 23 tokens per session scan A 324ed98729c4
AI酱瓜 is an agent published in the GitHub repository uluckyXH/OpenMOSS (1,315 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 1,848 once invoked, about $0.0001 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 2026-08-30.
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.