CkSKILLS: Skill for Claude Code

.agents/skills/hunt-clueboard/SKILL.md

hunt-clueboard is a skill for Claude Code, Codex from zhaji2333/CkSKILLS. It costs 103 tokens per session (1,445 once invoked), scanned A, original, MIT.

A Markdown clue board for preserving research findings, leads, assumptions, and disproven evidence across coding-agent sessions.

In plain words
What is it for?
It is for tracking reconnaissance, code and JavaScript clues, paths, keys, evidence, and next steps during security research.
Why use it?
It prevents important investigation details from being lost after a context reset, session change, or long research process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is zhaji2333/CkSKILLS's own configuration. It tells Claude Code and Codex how to work on CkSKILLS itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CkSKILLS configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/zhaji2333/CkSKILLS/main/.agents/skills/hunt-clueboard/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zhaji2333/CkSKILLS

Made for: Claude Code, Codex.

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 hunt-clueboard

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhaji2333/ckskills/hunt-clueboard/github.svg)](https://agentmods.dev/skills/zhaji2333/ckskills/hunt-clueboard)
Your own site
<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.

agentmods 80×15 button for hunt-clueboard

Your own site · 80×15
<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>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,445 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 $0.00103 $0.01445
Opus 5 $0.00051 $0.00723
Sonnet 5 $0.00021 $0.00289
Haiku 4.5 $0.00010 $0.00145

Measured 7d ago against content hash 6e50c5064174, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

.agents/skills/hunt-clueboard/SKILL.md · 104 lines

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 reportreport 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

  1. 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。
  2. 当轮写回。 线索不进板,本轮收集不算完成。禁止「等下再整理」。
  3. 板是台账不是日记。 只写判断、出处、状态、下一步。
  4. 否定证据优先。 主站没有、SPA 壳、NXDOMAIN、错字段 [] 必须进第 4 节。
  5. 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-h5api-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)

  1. hunts/<短名>/CLUEBOARD.md,没有就从模板复制。
  2. 读第 0/1/4/6 节,把「当前焦点」当成本轮第一任务。
  3. 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。

Read the full file on GitHub · 104 lines

Files

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.

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. 7d ago First seen · 104 lines · 103 tokens per session scan A 6e50c5064174

Subscribe to this mod's changes

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.