Borrowing it
Nothing to install: this file belongs to zhaji2333/CkSKILLS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zhaji2333/CkSKILLS/main/.agents/skills/hunt-clueboard/SKILL.mdgit clone --depth 1 https://github.com/zhaji2333/CkSKILLSWrote 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/zhaji2333/ckskills/hunt-clueboard)<a href="https://agentmods.dev/skills/zhaji2333/ckskills/hunt-clueboard"><img src="https://agentmods.dev/badge/skills/zhaji2333/ckskills/hunt-clueboard/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.
<a href="https://agentmods.dev/skills/zhaji2333/ckskills/hunt-clueboard"><img src="https://agentmods.dev/badge/skills/zhaji2333/ckskills/hunt-clueboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.01445 |
| Opus 5 | $0.00051 | $0.00723 |
| Sonnet 5 | $0.00021 | $0.00289 |
| Haiku 4.5 | $0.00010 | $0.00145 |
Grade A, and why
hunt-clueboard 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 7d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hunt-clueboard — 当前目标线索板(工作记忆)
薄过程 skill,对标 report:report 收口成稿,本 skill 把线索从对话里拿出来落盘。不挖洞、不替代 recon-js-analysis / unauth-path-key-hunt。
定位:低配黑板架构。 专项 Skill 是知识源(往板上写假设与证据),CLUEBOARD.md 是黑板(共享工作记忆),AGENTS.md 路由 + 板上「当前焦点」是控制(决定下一步调谁)。仍是单 Agent 顺序调度,不是多知识源并行抢写。
没有板,压缩或换会话后会从主站 JS 重开一局,否定证据(SPA 壳、405、空数组、NXDOMAIN)最先丢。
何时调用
- 新目标开工、攻击面梳理开始
- 用户说「线索板 / 写板 / 读板 / 建板 / 继续挖」
- 会话压缩后续挖、换人/换会话接着测
- 本轮产生了 Host/路径/密钥/证伪结果,必须写回
不要调用
- 还在问「要不要做线索板」的概念题 → 直接按本文建板
- 漏洞已确认只成稿 →
report(成稿前读板上「已证实」行) - 拆 JS / 打未授权 / 打越权本身 → 对应挖洞 skill;本 skill 只规定读写
和挖洞 skill 的关系
开工 → hunt-clueboard 建/读板
│
├─ 脏收集 / webpack → recon-js-analysis → 写回 1/2/3/5
├─ 零身份路径与钥 → unauth-path-key-hunt → 写回 2/3/4/7
├─ 角色 / IDOR → auth-access-control → 写回 2 鉴权列
├─ 全方法 / BOLA → api-protocol-security
└─ 成稿 → report(只读已证实)
铁律
- 先读后挖。 板上已证伪的 Host/路径本轮禁止当新发现再扫一遍。
- 当轮写回。 线索不进板,本轮收集不算完成。禁止「等下再整理」。
- 板是台账不是日记。 只写判断、出处、状态、下一步。
- 否定证据优先。 主站没有、SPA 壳、NXDOMAIN、错字段
[]必须进第 4 节。 - PII 不进板。 字段名和条数可以写;完整银行账号/手机/证件不写。原料进
raw/。
文件位置
hunts/<目标短名>/CLUEBOARD.md
hunts/<目标短名>/raw/ ← 可选,JS 摘录、响应头,禁止完整 PII
短名用 Host 主干,如 shop-h5、api-gw。一份目标一块板,不把多系统揉进一个文件。
建板:复制本 skill 目录 CLUEBOARD.template.md → 填目标短名和开工日。已有板则只读补写,不另起。
读写协议
开工(每轮对话第一次碰这个目标)
- 找
hunts/<短名>/CLUEBOARD.md,没有就从模板复制。 - 读第 0/1/4/6 节,把「当前焦点」当成本轮第一任务。
- 再调
recon-js-analysis/unauth-path-key-hunt等。
挖的过程中
每条可复用判断立刻追加到对应表,状态四选一:假设 / 已证伪 / 已证实 / 待打。
| 产出 | 写入 |
|---|---|
| 新 Host、301、同 IP | §1 |
路径/方法、405、data:[] |
§2 |
| getRsaKey、JSEncrypt、字段名 | §3 |
| 扫过但无效 | §4 |
| appid/密钥(打码) | §5 |
| 下一步动作 | §6 |
| ✅/❌/🔄/💡 | §7 |
出处必须能指到公开面(JS 文件、urlscan、兄弟域指纹)。没有出处的路径保持 假设。
指纹怎么分类,见 unauth-path-key-hunt P2,此处不重复。
收工(本轮结束前)
- 更新「当前焦点」为下一轮第一件事
- 假设仍超过 5 条就删最弱的或标证伪
- 板超过约 200 行:判断留在板上,原料搬
raw/
下「无此接口」之前
板上必须能看到失败升级已到 L4(网关 Host + 405/业务 JSON)。见 unauth-path-key-hunt P7。不到 L4 不准用主站 404 结案。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 104 lines · 103 tokens per session scan A 6e50c5064174
hunt-clueboard is a skill published in the GitHub repository zhaji2333/CkSKILLS (80 stars, last pushed 11d ago), licensed MIT. It adds 103 tokens to every session and 1,445 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
officecli-data-dashboard
Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to…
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
gpt-image-2
A skill for generating or editing images with GPT Image 2 across local, host-provided, or advisory setups.
new
Create a new project to start development quickly.