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/ranxi2001/zero2agent/new-articlenpx skills add ranxi2001/zero2Agent --skill new-articlegit clone --depth 1 https://github.com/ranxi2001/zero2AgentWhat 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 | $0.00124 | $0.01467 |
| Opus 5 | $0.00062 | $0.00733 |
| Sonnet 5 | $0.00025 | $0.00293 |
| Haiku 4.5 | $0.00012 | $0.00147 |
Grade A, and why
new-article 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
new-article:创建新文章
本技能用于在 zero2Agent 项目中创建符合项目风格的新学习文章。
项目约定
目录结构
{module-dir}/
└── {NN}-{slug}/
└── index.md
{NN}是两位数编号,如01、09、10{slug}是英文小写、用连字符连接,如tool-calling-basics- 每篇文章独占一个子目录,主文件统一命名为
index.md
已有模块目录
| 模块 | 目录 | 已有文章数 |
|---|---|---|
| Agent Basic | learn-agent-basic/ |
08 篇 (01–08) |
| Agent Survey | learn-agent-survey/ |
13 篇 (01–13) |
| Agent Training | learn-agent-training/ |
06 篇 (01–06) |
| Agent Interview | learn-agent-interview/ |
08 篇 (01–08),含面经实录 |
| LangGraph | learn-langgraph/ |
07 篇 (01–07) |
| Claude Code | learn-claude-code/ |
12 篇 (01–12) |
| SDK Frameworks | learn-sdk-frameworks/ |
04 篇 (01–04) |
| OpenClaw | learn-openclaw/ |
09 篇 (01–09) |
| Final Project | final-project/ |
0 篇 (占位符) |
Frontmatter 格式
---
layout: default
title: {文章标题(中文)}
description: {一句话描述,10–25 字}
eyebrow: {Module Name} / {NN}
---
eyebrow 示例:Agent Basic / 09、LangGraph / 01
文章写作风格(必须遵守)
zero2Agent 的读者是懂代码、懂深度学习基础的开发者,但对 Agent 工程实践还不熟悉。写作时:
- 问题优先:先说“为什么要关心这个问题”,再讲概念和方案。不要一上来就定义。
- 工程视角:解释概念时,要说清楚它在系统里扮演什么角色,而不是给出教科书定义。
- 避免框架崇拜:不要把某个框架讲成“最佳答案”,要讲清楚它解决什么问题、有什么代价。
- 暴露真实复杂度:要主动提到“这里容易踩坑”、“Demo 能跑但生产不行”。
- 精炼、不废话:不加不必要的修饰语,每个段落有实际内容。
- 使用代码块和图表:需要展示执行流程时优先用
```text代码块而不是大段描述。需要正式图表时默认使用```mermaid,包括多阶段管线、对比关系、架构分层和复杂流程,并按mermaid-check验证兼容性。仅当 Mermaid 无法可靠表达所需布局,或用户明确要求可编辑 Draw.io 画布时,才使用drawio-skill生成.drawio源文件和渲染资产。 - 文末导航:在最后用
下一篇建议继续看:+ 链接收尾(或说明尚无后续)。
文章结构模板
---
layout: default
title: {标题}
description: {一句话描述}
eyebrow: {Module} / {NN}
---
# {标题}
{开篇:1–3 句话,说明这个话题在实际工程中为什么重要 / 常见误解是什么}
## {核心概念或问题拆解}
{正文……}
## {深入一层:机制 / 设计原则 / 常见坑}
{正文……}
## {实践建议 或 典型误区}
{正文……}
## 小结
{用 3–5 个 bullet 提炼核心观点,不重复正文措辞}
下一篇建议继续看:
- [{下一篇标题}]({相对路径}/index.html)
面试模块特殊格式(learn-agent-interview)
该模块有两类文章,格式不同:
维度拆解文章(01–07)
按考察维度分类,每道题用“新手答 vs 高手答”对比格式:
## Q:{面试题}
> 来源:{公司/岗位}
**新手答**:"{浅层回答}"
**高手答**:
{深度回答,分层递进,带具体方案}
**差距在哪**:{分析新手和高手答案的差距,点出面试官真正在考什么}
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 · 145 lines · 124 tokens per session scan A 041db3075d7f
new-article is a skill published in the GitHub repository ranxi2001/zero2Agent (367 stars, last pushed 3d ago), licensed MIT. It adds 124 tokens to every session and 1,467 once invoked, about $0.0006 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 skills, from other repositories
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
hive.terminal-tools-fs-search
Use terminalrg / terminalglob for all filesystem search — your project tree as well as system configs, /var/log, /etc, archive contents. Teaches the rg vs glob vs terminalexec("find/ls/du/tree") split, common rg flag combos for code/logs/configs, glob patterns for finding files by name, the rule that mtime/size/type…
hive.terminal-tools-job-control
Use when launching anything that runs longer than a minute, anything that streams logs, anything you want to keep running while doing other work — or when terminalexec auto-backgrounded on you and returned a jobid. Teaches the start→poll→wait pattern with terminaljoblogs offset bookkeeping, the waituntilexit=True…
hive.terminal-tools-pty-sessions
Use when you need state across calls — building env vars, navigating with cd, driving REPLs (python -i, mysql, psql, node), or responding to interactive prompts (sudo password, ssh host-key confirmation, mysql connection). Teaches the prompt-sentinel exec pattern (default mode), raw I/O for REPLs (rawsend=True then…
llmtornado-tutorial-generator
Generates comprehensive code tutorials on LlmTornado API formatted for Medium publication with examples, explanations, and best practices.