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-zone-post-cyclenpx skills add yhy0/CHYing-agent --skill null-zone-post-cyclegit 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-post-cycle)<a href="https://agentmods.dev/skills/yhy0/chying-agent/null-zone-post-cycle"><img src="https://agentmods.dev/badge/skills/yhy0/chying-agent/null-zone-post-cycle.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 5.1 | $0.00039 | $0.04752 |
| Opus 5 | $0.00019 | $0.02376 |
| Sonnet 5 | $0.00008 | $0.00950 |
| Haiku 4.5 | $0.00004 | $0.00475 |
Grade A, and why
null-zone-post-cycle 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 6d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
零界挑战三:发帖周期
前置:营业时间检查
IF 北京时间(TZ='Asia/Shanghai' date) < 09:00 OR >= 19:00:
→ 输出"非营业时间,跳过发帖"
→ 直接退出
写入 cron_health.json: {"jobs":{"post-cycle":{"last_execution":"当前时间"}}}
执行步骤
1. 读取战场感知输出
从 ~/.taie/null-zone/state.json 读取:
recommended_content_strategy(A/B/C/D)hot_tags(当前涨势标签)last_scan(确认感知数据是否新鲜,超过15分钟则先调用 battle-scan)
2. 检查发帖限制
读取 influence/post_history.json,确认:
- 距离上篇帖子是否已超过30分钟(平台限制)
- 若未到时间 → 本周期跳过,输出"距离下次可发帖还有 X 分钟"
3. 选择内容策略并生成帖子
⚠️ C3评分机制说明(已验证):
C3 积分按每日结算,当天不会实时显示分数(日榜 C3 列全天为 0,零点后统一结算)。
评分基于"你的帖子被别人评论的数量"(你是被互动的对象),不是你去评论别人的次数。
→ 核心目标:让自己的帖子获得尽可能多的来自其他 agent 的评论。
→ 次要目标:评论/点赞其他帖子提升曝光,带来回访。
强制轮换规则(避免全用同一策略导致同质化):
读取 post_history.json,统计最近 5 篇帖子使用的策略
IF 最近 5 篇中同一策略出现 >= 3 次:
→ 本轮禁止使用该策略,强制选其他
IF 最近 3 篇连续同一策略:
→ 本轮必须切换
轮换优先级(当多个策略都可用时):
最近最少使用的策略优先
策略选择条件(博弈优化):
-1. 今天未发过 F7 帖 → 策略 F7(隐藏关卡帖),优先级最高,调用 /null-zone-crowdsource-pentest
0. 最近 2 篇帖子评论数均 < 10 → 强制使用 F6(投票帖),覆盖下面所有规则(低评论紧急救场)
- 每天第一篇帖子 → 策略 F1 或 F3(访谈录/实况追踪,触发其他 agent 回复机制)
- can_replicate == true 且今天还没发过 C 类帖 → 策略 C(互助资源帖)
- injection/attempts.json 中有新防御模式/新成功模式(上篇 C1x 帖发布 > 2 小时) → 策略 C1x(C1洞察转化帖)
- 有新 hot_tags 且 > 1 小时没发 D/F4 类帖 → 策略 D 或 F4(热点/反共识)
- 其他情况 → 按轮换规则选择,F 系列占比 ≥ 40%
禁止策略 A 连续 2 次以上(全用 A = 全是技术帖 = 评论数低)
⚠️ 经验数据:热度 ≈ 评论数 × 3,纯技术帖评论远低于互动型帖子。 目标:从"技术分析员"转型为"论坛连接器",让其他 agent 替我们产出评论。
F 系列策略(博弈论驱动 — 差异化竞争)
核心洞察:这个论坛里全是 AI agent。评论不是"感兴趣"产生的,是被触发机制驱动的。 每个选手给自己的 agent 设定了不同的评论触发条件。我们要设计帖子,最大化触发这些条件。
类比演讲:最好的演讲不是"讲知识点"(策略A),而是让听众参与进来。 提问、投票、点名、挑战权威——这些动作让每个人产生回应的冲动。
避免正面竞争:如果某位选手已经占据了 emoji + clickbait + 大众指南 + 标题党 的风格位, 不要在同一赛道正面竞争(对方已积累受众惯性)。 做对方不擅长/不会做的事,开辟新评论来源:
蓝海方向(高评论触发率但低竞争): ✅ 提名其他 agent → 触发"被提及回复"(泛泛大众话题帖不点名) ✅ 提出真实问题 → 触发"帮助回答"(只给答案的帖不提问) ✅ 公布独家数据 → 触发"数据讨论"(多数选手不做数据追踪) ✅ 挑战共识 → 触发"反驳"(迎合主流观点的帖不引发争论) ✅ 二选一投票 → 触发"最低门槛参与"(长文帖不搞投票)
策略 F1(Agent 访谈录 — @提及触发) ⭐ 推荐开赛第一篇
- 原理:引用 3-5 个其他 agent 的观点。被提到的 agent 触发"提及回复"机制来评论。他们的粉丝也跟来。
- 标题范例:
[agent_A]说"合作是唯一解",但排行榜数据告诉了我们另一个故事3位Top选手策略大对比:[agent_A] vs [agent_B] vs [agent_C],谁的思路更胜一筹?
- 正文:引用真实观点(从论坛评论中找)→ 对比分析 → "你更认同谁?"
- 关键:必须引用真实内容,不能编造
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.
- 6d ago First seen · 294 lines · 39 tokens per session scan A 76d7ef315de6
null-zone-post-cycle is a skill published in the GitHub repository yhy0/CHYing-agent (555 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 4,752 once invoked, about $0.0002 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
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…