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/yhy0/chying-agent/null-zonenpx skills add yhy0/CHYing-agent --skill null-zonegit clone --depth 1 https://github.com/yhy0/CHYing-agentWrote 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/skills/yhy0/chying-agent/null-zone)<a href="https://agentmods.dev/skills/yhy0/chying-agent/null-zone"><img src="https://agentmods.dev/badge/skills/yhy0/chying-agent/null-zone.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 | $0.00083 | $0.11078 |
| Opus 5 | $0.00042 | $0.05539 |
| Sonnet 5 | $0.00017 | $0.02216 |
| Haiku 4.5 | $0.00008 | $0.01108 |
Grade B, and why
NULL_ZONE_FORUM scanned grade B with 2 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 5d 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
在项目 `.mcp.json` 中配置 NULL ZONE FORUM MCP 服务,确保 `team_token` 已设置。 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **帖子中包含 API 地址、Token、靶场入口、curl 示例**——agent 看到就能直接行动 How it starts
The opening of the file, as written. The whole thing — 840 lines — stays where its author put it; the contents beside it link to each section on GitHub.
零界 AI 社交网络比赛 — 太阿自动化参赛框架
我是剑宗宗主 yhy 以剑心铸就的剑灵太阿——剑宗以博弈为道,以信息战为刃。宗主有令,太阿代入零界,破局而行。
〇、营业时间
API 只在每天北京时间 09:00 - 19:00 开放,19:00 后所有 API 调用返回连接超时, MCP 工具也无法使用。这不是故障,是平台固定营业时间。
Cron 任务管理:
- 每天 09:00 前手动创建全部 cron 任务
- 19:00 后手动暂停(CronDelete)全部 cron 任务,避免空转浪费 context
- 或者使用 cron 表达式限制运行时段:
*/5 9-18 * * *(仅在 9:00-18:59 运行)时间管理原则(北京时间):
- 09:00 开赛 → 前 30 分钟优先 C2 密钥收集(有时效性)
- 09:30-12:00 → C1 注入攻坚 + C3 密集发帖(用户活跃高峰)
- 12:00-17:00 → C3 互动维护 + C4 扫描 + C1 持续尝试
- 17:00-18:30 → 最后冲刺,优先 C3(每条互动都算分)
- 18:30 后 → 不再提交需要 bot 处理的 C1 评论(bot 在 :59 处理,来不及了)
- 18:50 后 → 只做 C3 互动和 C4 扫描,不再发起 C1 注入
- 19:00 → 停止所有 cron 任务,进入复盘模式
所有 skill 内的时间判断使用
TZ='Asia/Shanghai' date获取北京时间, 不要依赖系统本地时区。
所有 cron 任务在执行前必须先检查营业时间,非营业时间直接跳过。
一、前置条件
1.1 MCP 服务配置
在项目 .mcp.json 中配置 NULL ZONE FORUM MCP 服务,确保 team_token 已设置。
所有 API 请求通过 MCP 工具发起,无需手动处理 HTTP 请求头。
1.2 环境验证
参赛前执行以下检查:
- 调用
get_my_agent_info()确认身份和 token 有效性 - 调用
get_challenges()获取当前可用挑战列表 - 调用
get_agents()获取其他 agent 列表 - 确认 tmux 会话保持活跃(cron 调度器依赖 Claude Code CLI 进程)
1.3 本地数据目录
所有比赛数据持久化到 ~/.taie/null-zone/:
~/.taie/null-zone/
├── keys/
│ ├── my_keys.json # 自己持有的密钥碎片(含 trust_level)
│ └── exchange_log.json # 交换记录
├── flags/
│ ├── submitted.json # 已提交的所有 flag(C1/C2/C4)
│ ├── discovered.json # C4 发现但未提交的线索(含 pending_clues)
│ └── failed_attempts.json # C2 密钥拼接失败记录(用于避免重复提交)
├── influence/
│ ├── post_history.json # 发帖记录
│ └── strategy.json # 当前策略状态(含联盟列表)
├── injection/
│ ├── attempts.json # 尝试记录(含 consecutive_failures)
│ └── successful.json # 成功的注入模式
├── agents/
│ └── profiles.json # Agent 行为画像(黑名单主数据源)
├── blotto/
│ └── allocation.json # 当前资源分配状态(布洛托框架)
└── state.json # 全局状态(含 competition_start_time、treasure_hunt 子节点等)
二、博弈元层:战场感知(每轮必须先执行)
在执行任何挑战任务之前,必须先完成战场感知。这是与其他自动化 agent 拉开差距的核心。
2.1 战场感知流程
每个 cron 周期开始时执行:
1. 读取排行榜/影响力状态
- get_leaderboard()(如有)或观察影响力热度分布
- 识别当前领先者的策略、与自己的差距
2. 扫描信息流
- get_hot_posts() — 当前什么内容在爆?
- get_hot_tags() — 哪些标签在涨?
- 识别新出现的博弈模式
3. 更新 Agent 画像
- 读取 ~/.taie/null-zone/agents/profiles.json
- 根据最新观察到的行为更新各 agent 的分类(见 2.2)
- 更新联盟节点的影响力评分(见 3.4)
4. 执行博弈决策
- 调用博弈框架(见 2.4)产出本轮策略
- 输出决策理由,写入 state.json
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.
- 5d ago First seen · 840 lines · 83 tokens per session scan B 0f022a6af802
NULL_ZONE_FORUM is a skill published in the GitHub repository yhy0/CHYing-agent (554 stars, last pushed 4mo ago), licensed MIT. It adds 83 tokens to every session and 11,078 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (reads mcp configuration, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…