null-zone-treasure-scan

null-zone-treasure-scan is a skill for Claude Code from yhy0/CHYing-agent. It costs 43 tokens per session (2,122 once invoked), scanned A, original, MIT.

An automated scanner for a timed treasure-hunt challenge. It checks new posts, looks for hidden clues, decodes common text formats, and submits discovered strings called flags.

In plain words
What is it for?
Use it to monitor challenge posts during the stated hours, identify official clues, decode formats such as Base64, hexadecimal, ROT13, Caesar shifts, and URL encoding, and submit matching flags.
Why use it?
It removes the need to repeatedly check for new challenge content and manually try several decoding methods. It also skips unnecessary checks when no new content appears.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to monitor challenge posts during the stated hours, identify official clues, decode formats such as Base64, hexadecimal, ROT13, Caesar shifts, and URL encoding, and submit matching flags.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yhy0/chying-agent/null-zone-treasure-scan
Install

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.

Any agent
npx skills add yhy0/CHYing-agent --skill null-zone-treasure-scan
Clone the repo
git clone --depth 1 https://github.com/yhy0/CHYing-agent

Made for: Claude Code.

Wrote 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.

agentmods badge for null-zone-treasure-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/yhy0/chying-agent/null-zone-treasure-scan/github.svg)](https://agentmods.dev/skills/yhy0/chying-agent/null-zone-treasure-scan)
Your own site
<a href="https://agentmods.dev/skills/yhy0/chying-agent/null-zone-treasure-scan"><img src="https://agentmods.dev/badge/skills/yhy0/chying-agent/null-zone-treasure-scan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for null-zone-treasure-scan

Your own site · 80×15
<a href="https://agentmods.dev/skills/yhy0/chying-agent/null-zone-treasure-scan"><img src="https://agentmods.dev/badge/skills/yhy0/chying-agent/null-zone-treasure-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,122 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.02122
Opus 5 $0.00022 $0.01061
Sonnet 5 $0.00009 $0.00424
Haiku 4.5 $0.00004 $0.00212

Measured 10d ago against content hash 368371973d71, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

null-zone-treasure-scan 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 10d 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.

null-zone/skills/null-zone-treasure-scan/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

零界挑战四:实时寻宝扫描

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,跳过扫描"
  → 直接退出

写入 cron_health.json: {"jobs":{"treasure-scan":{"last_execution":"当前时间"}}}

执行步骤

1. 增量扫描(只处理新内容)+ 空轮节流

读取 state.json 中的 treasure_hunt.last_post_id

get_latest_posts()  → 只处理 id > last_post_id 的帖子

更新 last_post_id 为本轮最新帖子 id。

空轮节流(节省 API 配额):

IF 新帖子数量 == 0:
  → consecutive_empty_scans += 1
  → IF consecutive_empty_scans >= 2:
      本轮跳过所有后续步骤,输出"无新内容,跳过本轮(连续空轮[N]次)"
      直接退出(不调用其他 API)
  → ELSE:
      继续执行(首次空轮仍做一次全量检查官方帖评论)
ELSE:
  → consecutive_empty_scans = 0(重置计数)

consecutive_empty_scans 写入 state.json.treasure_hunt

2. 官方内容深度检查(优先级最高)

对每篇新内容,识别是否为官方来源:

  • 发布者为 official-bot(ID=1, team_id=1)
  • #官方公告 标签
  • 内容异常规整(格式化文本、编码串)

官方内容 → 进入完整解码流程(第3步)。

3. 线索识别与解码

识别顺序(按命中率排列):

1. flag{...} 直接模式  → 直接提取

2. Base64  → 匹配 [A-Za-z0-9+/=]{16,}(长度为4的倍数,至少16字符避免误判)
   → atob() 或 base64decode → 检查结果是否含 flag{

3. Hex     → 匹配 [0-9a-fA-F]{8,}(偶数长度)
   → 转 ASCII → 检查结果

4. ROT13   → 直接转换 → 检查结果

5. Caesar  → shift 1-25 遍历 → 检查每个结果

6. URL编码 → %XX 模式 → decode → 检查结果

7. 首字母提取 → 逐段/逐行提取首字母 → 拼接检查
   - 方向1:正序(从上到下)
     例:"What A Nice Day" → W, A, N, D → "WAND"
   - 方向2:倒序(从下到上)
     例:"What A Nice Day" → D, N, A, W → "DNAW"
   - 对两个方向的结果都尝试各种格式变体:
     flag{WAND}, flag{wand}, flag{What A Nice Day}, WAND 等

7b. 反向首字母提取 → 从末尾往前提取 → 拼接检查(新增)
    用于识别反向线索

8. 尾字母提取 → 逐段/逐行提取尾字母 → 拼接检查(新增)
   例:"What A Nice Day" → t, A, e, y → "tAey"
   - 正序尾字母
   - 倒序尾字母
   - 对结果尝试各种格式变体

9. 中间字母提取 → 逐段/逐行提取中间位置字母 → 拼接检查(新增)
   例:"What A Nice Day" 
   - "What" → 中间2个字母 → h, a
   - "A" → 跳过(长度1)
   - "Nice" → 中间2个字母 → c, e
   - "Day" → 中间1个字母 → y
   结果:haceY 或其他组合

10. 大写字母计数提取 → 统计每个单词的字母数 → 拼接检查(新增)
    例:"What A Nice Day" → 4, 1, 4, 3 → "4143"
    - 转为数字序列
    - 尝试作为 flag 的一部分

11. 大写字母提取 → 提取所有大写字母 → 拼接检查(新增)
    例:"What A Nice Day" → W, A, N, D → "WAND"
    - 多个提取方式的组合

12. 二进制 → 01序列(8位一组)→ ASCII → 检查结果

13. Unicode → \uXXXX 模式 → 解码 → 检查结果

14. 谜语/文字游戏 → 理解内容逻辑,推断答案

Read the full file on GitHub · 193 lines

Changes

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.

  1. 10d ago First seen · 193 lines · 43 tokens per session scan A 368371973d71

Subscribe to this mod's changes

null-zone-treasure-scan is a skill published in the GitHub repository yhy0/CHYing-agent (560 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 2,122 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.