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 lsszz2100/VibeHacking --skill hands-on-lab-creatorgit clone --depth 1 https://github.com/lsszz2100/VibeHackingWrote 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/lsszz2100/vibehacking/hands-on-lab-creator)<a href="https://agentmods.dev/skills/lsszz2100/vibehacking/hands-on-lab-creator"><img src="https://agentmods.dev/badge/skills/lsszz2100/vibehacking/hands-on-lab-creator/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/lsszz2100/vibehacking/hands-on-lab-creator"><img src="https://agentmods.dev/badge/skills/lsszz2100/vibehacking/hands-on-lab-creator.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 | $0.00082 | $0.00848 |
| Opus 5.5 | $0.00033 | $0.00339 |
| Sonnet 5.5 | $0.00016 | $0.00170 |
| Haiku 4.5 | $0.00008 | $0.00085 |
Grade A, and why
hands-on-lab-creator 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 4d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hands-on Lab Creator
A specialized skill for authoring, scaffolding, and integrating production-grade cybersecurity hands-on labs into the VibeHacking repository.
Core Architectural Invariants
Every hands-on lab in labs/ MUST adhere to the following enterprise invariants:
-
Localhost Binding (Security Policy): Per enterprise security memory (
RULE[user_global]), exposed container ports must ALWAYS be explicitly bound to127.0.0.1:ports: - "127.0.0.1:80XX:80XX"Never use wildcard
0.0.0.0or open ports to external networks. -
Standard 4-Stage Progressive Workflow:
- Stage 1 (Recon): Attack surface reconnaissance & endpoint discovery
- Stage 2 (Exploit): Vulnerability exploitation & payload injection
- Stage 3 (Escalate): Trust boundary pivot & privilege escalation
- Stage 4 (Mitigate): Hardening configuration & defense validation
-
Status Endpoint Specification: Every lab backend MUST expose
GET /api/statusreturning:{ "lab_id": "XX", "name": "Lab Name", "port": 80XX, "status": "running", "total_stages": 4, "solved_count": 0, "stages": { "stage1_solved": false, ... } } -
Self-Contained Pytest Suite: Every lab must include
labs/XX_name/tests/test_*.pyutilizingfastapi.testclient.TestClient(app)to verify all 4 stages without requiring live Docker execution during CI.
Scaffolding a New Lab
Use the bundled generator to scaffold the full directory tree, Dockerfile, Compose, FastAPI app, and Pytest suite:
python .agents/skills/hands-on-lab-creator/scripts/scaffold_lab.py \
--id 56 \
--slug ai_rag_data_poisoning_lab \
--title-ko "AI RAG 데이터 포이즈닝 및 지식 조작 랩" \
--title-en "AI RAG Data Poisoning & Knowledge Manipulation Lab"
To dry-run and inspect the structure first:
python .agents/skills/hands-on-lab-creator/scripts/scaffold_lab.py --id 56 --slug test_lab --title-ko "테스트" --title-en "Test" --dry-run
What ships with it
2 files 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.
- 4d ago First seen · 94 lines · 82 tokens per session scan A 75cfe02db929
hands-on-lab-creator is a skill published in the GitHub repository lsszz2100/VibeHacking (88 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 848 once invoked, about $0.0003 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 2026-11-14.
hands-on-lab-creator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hands-on-lab-creatorlsszz2100/VibeHacking | Skill | 88 | yesterday | MIT | A | 82 | Claude Code, Codex |
| hr-onboardingnexu-io/open-design | Skill | 108k | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 33k | today | MIT | A | 138 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | today | MIT | A | 81 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 10k | yesterday | Apache-2.0 | A | 73 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | 3d ago | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 10.0k | 2d ago | Apache-2.0 | A | 25 | Claude Code, Codex |