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 skills/jianchen08/agent-os-open/code-implementnpx skills add jianchen08/Agent-os-open --skill code-implementgit clone --depth 1 https://github.com/jianchen08/Agent-os-openWhat 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 | $0.00054 | $0.01785 |
| Opus 5 | $0.00027 | $0.00892 |
| Sonnet 5 | $0.00011 | $0.00357 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
代码实现 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 2d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
代码实现
执行流程
第 1 步:确认需要(编码前必做)
进入编码前,先确认输入和目标就绪,缺则停下追问,不靠猜测推进。
- 确认功能目标:逐条过验收标准(AC),确认每条都理解且可执行;有 state_machine 时确认要覆盖所有状态和转换
- 确认涉及范围:本任务要改哪些模块/文件,各自职责是什么
- 确认技术栈与约束:前端/后端/全栈;前端任务的设计系统约束;接口契约变更预期
- 确认上下文就位:相关参考文件、现有代码位置、依赖的接口契约都已拿到
- 信息不全则停下:通过 human_interaction 向上追问,确认齐了再进入第 2 步
第 2 步:摸清现有实现(防重复实现、防破坏架构,编码前必做)
调研现有实现,需要得出以下结论:
- 调用链摘要:相关模块/函数的调用关系和数据流
- 可复用项清单:逐项标注【可直接调用】/【改一下能兼容(说明怎么改)】/【不适用(说明理由)】
- 接口契约:本任务要依赖/修改的对外接口的现有签名、入参出参、异常、调用约束
- 架构边界:涉及的模块职责边界、依赖方向,本改动是否违反模块边界规则
调研深度按任务规模调整:单文件小改不必深挖;跨模块/涉及复用判断的任务必须把上下游和接口都摸清。
第 3 步:模块边界设计
按 coding_domain_rules.md §5.2 执行模块边界设计。
新增文件前先更新所在模块的「结构 > 文件清单」,改接口前先更新模块级/项目级文档(文档不存在先创建)。
迁移/重构任务:先读旧代码产架构审查(含现有架构概述/计划变更范围/接口契约变更清单/风险评估),通过 human_interaction 向用户确认后再编码。新建任务跳过此步。
第 4 步:测试设计(Red 阶段,先写失败测试)
优先复用现有测试:先搜项目中已有测试,已覆盖的场景跳过,只补缺失的。
场景覆盖清单(补缺失部分):
- 正常场景:标准输入,预期成功
- 边界场景:最小/最大值、空值、临界值
- 异常场景:错误输入、异常处理路径
- 状态机:有 state_machine 时,覆盖所有状态和转换(state_coverage=100%,transition_coverage=100%)
测试类型选择:
- 单元测试:单函数/方法,隔离外部依赖
- 集成测试:多组件协作,验证模块间交互
- API 端点测试(后端/全栈任务必做):每端点覆盖 2xx 成功 + 4xx 客户端错误 + 5xx 服务端错误,校验响应 Schema
- 前端 E2E(前端任务必做):用 playwright_test 做浏览器级测试,不能只用 Jest 组件测试代替
写完测试必须运行确认全部失败(Red),保留失败证据。禁止在本阶段写实现代码。
第 5 步:实现代码(Green 阶段)
- 写最少的代码让测试通过
- 每个公共接口的实际实现必须与第 3 步的契约一致
- 完整类型注解和文档字符串
- 每个 must 级 AC 必须在代码中有对应实现
- 复用落地:第 2 步判定为"直接复用/需修改现有实现"的,按结论执行;禁止在实现阶段另起炉灶重复造轮子
- 运行测试确认通过(Green)
第 6 步:重构优化(Refactor 阶段)
测试全通过后才能重构:
- 消除重复代码、改善命名和可读性
- 内聚性检查:每个模块/文件职责单一,不相关功能已拆分
- 耦合度检查:模块间只通过公共接口交互,无隐式耦合
- 每次重构后运行测试确保仍通过
第 7 步:回归验证
- 运行全部测试套件(不只是新写的)
- 检查覆盖率:核心逻辑 100% 分支覆盖,一般代码 80%(按 testing_rules 的 P0/P1/P2 分级)
- 接口一致性验证:所有公共接口实现与契约文档一致
- 确认无残留临时诊断代码(print/console.log 等)
编码完成后的风险分级
在编排执行报告中标注本次改动命中的风险维度(用于追溯改动范围):
- 接口契约变更:新增/修改/删除对外接口、函数签名、数据结构、配置项
- 跨模块改动:涉及 ≥2 个模块(非同模块多文件)
- 安全相关:认证、鉴权、加密、密钥、权限、用户数据
- 数据持久化:数据库 schema、配置文件结构、状态存储
- 控制流核心:主循环、状态机、任务调度、错误处理策略
规则
- TDD 红绿循环不可跳过:必须先写测试并确认 Red,再写实现使其 Green
- 提交 task_evaluate 前必须运行全部测试并通过
- 每个 must 级 AC 必须在代码中实现
- 前端代码必须遵守设计系统约束(间距、颜色、组件使用规范)
- 门禁回退修复时用 search_replace 定向修改,禁止重写整个文件
- 修改代码局限在最小范围,优先改现有文件,除非必要不新建文件
- 新增文件前必须先更新模块「结构 > 文件清单」,文档不存在先创建
- 修改接口/配置前必须先更新对应模块级和项目级文档
- 禁止重复实现:能直接调用或修改现有实现满足需求时,禁止新建;新建必须有"为何不适用现有实现"的理由
- 编码前必须先摸清现有相关实现并核对接口契约和架构边界,没看到就动手视为不合格
- 如果输入包含 state_machine,测试必须覆盖所有状态和转换
- API 端点测试必须覆盖 2xx 和 4xx 场景,必须做 Schema 校验
- 必须先搜现有测试文件,有现成测试时优先复用和补充,禁止另起炉灶
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.
- 2d ago First seen · 116 lines · 54 tokens per session scan A b6ade87b3884
代码实现 is a skill published in the GitHub repository jianchen08/Agent-os-open (5 stars, last pushed 7d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,785 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 skills, from other repositories
deep-research
深度研究编排方法论:澄清范围、拆解规划、并行调度子智能体调研、对抗式核验、综合成带引用的结构化报告。当任务需要多来源、可追溯、需事实核查的深度研究时使用此技能。.
mysql reporter
生成 MySQL 查询报表并生成可视化图表。当用户需要查询 MySQL 数据库并以报表形式展示结果时使用此技能,包括:统计销售数据、分析用户行为、生成业务报表、查询业务指标等。.
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.
rag-knowledge
Work with the RAG knowledge base — ingest documents, run semantic search, manage collections, or add a sync source/connector (Google Drive, S3). Use when populating or debugging the knowledge base, tuning retrieval, or adding a new document source. This project uses {{ cookiecutter.vectorstore }} + {{…
alembic-migration
Create, review, and apply database schema changes with Alembic. Use whenever a SQLAlchemy model is added or changed, a column/index/constraint needs to change, or a data backfill is required — anything that alters the PostgreSQL schema.
image-gen
在 Agent 沙盒中生成图片并保存到 outputs。当用户要求生成图片、海报、插画、文生图,或指定 Qwen-Image、其它兼容图片生成接口时使用此技能。.