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 Liberty91LTD/cti-skills --skill dprk-cyber-espionagegit clone --depth 1 https://github.com/Liberty91LTD/cti-skillsWrote 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/liberty91ltd/cti-skills/dprk-cyber-espionage)<a href="https://agentmods.dev/skills/liberty91ltd/cti-skills/dprk-cyber-espionage"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/dprk-cyber-espionage/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/liberty91ltd/cti-skills/dprk-cyber-espionage"><img src="https://agentmods.dev/badge/skills/liberty91ltd/cti-skills/dprk-cyber-espionage.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 | $0.00075 | $0.03198 |
| Opus 5 | $0.00037 | $0.01599 |
| Sonnet 5 | $0.00015 | $0.00640 |
| Haiku 4.5 | $0.00007 | $0.00320 |
Grade A, and why
dprk-cyber-espionage 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 12d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DPRK Cyber Espionage Knowledge Cell
Executive Summary
North Korea operates a uniquely structured cyber program where revenue generation and intelligence collection are equally prioritized national objectives. Under the Reconnaissance General Bureau (RGB), DPRK cyber operators have stolen an estimated $3-6 billion in cryptocurrency and financial assets since 2017, making the cyber program one of the regime's primary sources of hard currency and a critical enabler of its nuclear and ballistic missile programs. This dual-purpose model distinguishes DPRK operations from all other nation-state cyber programs, where espionage is typically the primary objective and financial operations are secondary or opportunistic.
The DPRK cyber ecosystem is organized into several distinct clusters operating under the RGB umbrella. Lazarus Group (Diamond Sleet/HIDDEN COBRA) is the most broadly capable unit, conducting both espionage operations against defense and aerospace targets and major financial theft operations. APT38/BlueNoroff specializes in financial sector targeting, including SWIFT network attacks and cryptocurrency platform compromise. Kimsuky (Emerald Sleet) focuses on espionage targeting South Korean government, research institutions, think tanks, and North Korea policy experts. Andariel (Onyx Sleet) conducts espionage against defense and nuclear technology targets, with secondary ransomware operations. These groups share tooling, infrastructure, and techniques while maintaining distinct operational mandates.
The period from 2022-2025 has been defined by three major trends: an explosive escalation in cryptocurrency theft (including the $625 million Ronin Network hack and the $1.5 billion Bybit exchange compromise), the expansion of the IT worker fraudulent employment scheme generating an estimated $250-600 million annually, and increasingly sophisticated supply chain attacks exemplified by the 3CX compromise. DPRK operators have demonstrated remarkable adaptability, pivoting quickly to target emerging DeFi protocols, cryptocurrency bridges, and Web3 infrastructure while maintaining persistent espionage campaigns against defense industrial base and nuclear technology targets aligned with regime weapons program priorities.
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.
- 12d ago First seen · 142 lines · 75 tokens per session scan A 2d40063715ea
dprk-cyber-espionage is a skill published in the GitHub repository Liberty91LTD/cti-skills (18 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 3,198 once invoked, about $0.0004 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
ai-ad-copy-compliance-review
A risk-review assistant for advertising and sales copy. It examines provided material for possible concerns and suggests actions.
ai-agent-browser
A business-diagnosis assistant for marketing, operations, product, and sales questions. It breaks down a goal and produces a summary, findings, action suggestions, and reusable deliverables.
ai-article
A Chinese-language assistant for turning source material into article and content-operation deliverables. It is aimed at creators, marketers, technical teams, and media publishers.
ai-brand-voice-review
A business-diagnosis assistant for marketing, operations, services, and sales questions.
ai-browser-use
A business-diagnosis assistant for marketing, operations, product, and sales questions about how to approach a task.
ai-content-material-audit
A Chinese-language copy-review assistant for creators, marketers, operators, and media teams.