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 skills add Rheinmir/setup --skill dym-cti-expert-investigate-in-claude-codegit clone --depth 1 https://github.com/Rheinmir/setupWrote 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/rheinmir/setup/dym-cti-expert-investigate-in-claude-code)<a href="https://agentmods.dev/skills/rheinmir/setup/dym-cti-expert-investigate-in-claude-code"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-cti-expert-investigate-in-claude-code/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/rheinmir/setup/dym-cti-expert-investigate-in-claude-code"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-cti-expert-investigate-in-claude-code.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.01614 |
| Opus 5.5 | $0.00024 | $0.00646 |
| Sonnet 5.5 | $0.00012 | $0.00323 |
| Haiku 4.5 | $0.00006 | $0.00161 |
Grade A, and why
dym-cti-expert-investigate-in-claude-code 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 yesterday.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym-cti-expert-investigate-in-claude-code — Điều tra bằng lệnh chat (CHỈ trong Claude Code)
Mọi lệnh trong file này là lệnh CHAT. Gõ vào terminal sẽ không chạy. Bản terminal ở 04-cli-dispatcher.md.
Vì sao dùng: đây là bề mặt mà cti-expert được thiết kế quanh — agent tự định tuyến theo loại target và tự chạy chuỗi công cụ.
Sinh ra cái gì: case trong intel_engine/cases/<CASE-ID>/, bảng domain hiển thị trong chat, và file export theo 06.
Đúng 8 lệnh được đăng ký
scripts/register.sh symlink 8 file trong commands/ vào ~/.claude/commands/. Đây là 8 lệnh duy nhất chạy được từ prompt nguội ở bất kỳ dự án nào:
| Lệnh | Làm gì | Op T2 tương đương | Tool T1 tương đương |
|---|---|---|---|
/cti <target> [--deep|--quick|--passive] |
điểm vào — định tuyến theo loại target | (cả chuỗi) | (cả chuỗi) |
/cti-recall <seed> |
đã gặp chưa? luôn chạy đầu tiên | recall |
domain_verdict, which_cases |
/cti-case <CASE-ID> <seed> [seed...] |
pipeline tất định đầy đủ | pipeline open |
(không có — chỉ CLI) |
/cti-pivot <url|domain|ip> [--passive] |
thu thập MỘT target | pivot-extract |
pivot_extract |
/cti-cluster <domain|CASE-ID> |
mở rộng & tương quan | kb, cert-overlap |
kb_cluster, cert_overlap |
/cti-check <indicator> |
kiểm soát dương tính giả | reference check |
reference_check, reference_add |
/cti-report <CASE-ID> [--graph|--pdf] |
render graph + PDF/DOCX | graph, report |
render_diagram, render_report |
/cti-status |
tier backend / MCP / credit | backend.py status |
api_usage |
Mọi /lệnh khác bạn thấy trong SKILL.md §3 (/case, /sweep, /query, /username, /flow, /brief...) là quy ước đọc từ file đó, không phải lệnh đã đăng ký. Sau khi skill đã nạp chúng là chỉ dẫn rõ ràng cho agent; gõ ở prompt nguội thì không có gì xảy ra. Khi phân vân: dùng /cti và mô tả mục tiêu bằng tiếng Việt/tiếng Anh bình thường.
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.
- yesterday First seen · 89 lines · 59 tokens per session scan A e06f1bfc7eb9
dym-cti-expert-investigate-in-claude-code is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 59 tokens to every session and 1,614 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.
dym-cti-expert-investigate-in-claude-code compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dym-cti-expert-investigate-in-claude-codeRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 59 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |