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 wargame-chall-buildergit 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/wargame-chall-builder)<a href="https://agentmods.dev/skills/lsszz2100/vibehacking/wargame-chall-builder"><img src="https://agentmods.dev/badge/skills/lsszz2100/vibehacking/wargame-chall-builder/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/wargame-chall-builder"><img src="https://agentmods.dev/badge/skills/lsszz2100/vibehacking/wargame-chall-builder.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 | $0.00091 | $0.00966 |
| Opus 5.5 | $0.00036 | $0.00386 |
| Sonnet 5.5 | $0.00018 | $0.00193 |
| Haiku 4.5 | $0.00009 | $0.00097 |
Grade A, and why
wargame-chall-builder 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.
Wargame Challenge Builder
A specialized skill for authoring, modifying, and strictly auditing challenges in the VibeHacking browser-based wargame engine.
Core Invariant: The 4-Stage Audit Gate
Every change to wargame/assets/challenges.js or wargame/README.md MUST pass all 4 audit gates before committing:
verify.js: Structural invariants, id uniqueness, Tier gates & HUD counts match.leakscan.js: Zero cross-challenge answer leaks in prompts and hints.audit.js --strict: Format precision ([G],[H]), zero topic table answer spoilers ([F]), zero stemming/plural ambiguities ([J]).solve-derivable.js: 100% automated solving of all derivable challenges.
Run the bundled pre-audit script before finishing any task:
python .agents/skills/wargame-chall-builder/scripts/pre_audit.py
Challenge Object Structure
Each challenge in wargame/assets/challenges.js must follow this schema:
{
"id": "t2_example_id",
"tier": 2,
"cat": "web",
"track": "web",
"points": 100,
"ci": true,
"hash": "<sha256 of lowercase trimmed plaintext>",
"fmt": "한 단어 / one word (8글자 / 8 chars)",
"title": {
"ko": "한글 제목",
"en": "English Title"
},
"prompt": {
"ko": "도전 과제 설명 및 질문",
"en": "Challenge description and question"
},
"hints": {
"ko": [
"첫 번째 점진적 힌트",
"결정적 힌트 (정답 평문 노출 금지)"
],
"en": [
"First progressive hint",
"Decisive hint (do not leak plaintext)"
]
}
}
Authoring Workflows
1. Generating Challenge Snippets with gen_challenge.py
Never hand-compute SHA-256 hashes or guess length qualifiers. Use the bundled generator:
# Calculate hash and length pinning for an answer
python .agents/skills/wargame-chall-builder/scripts/gen_challenge.py --answer "credentials"
# Validate a complete JSON definition
python .agents/skills/wargame-chall-builder/scripts/gen_challenge.py --json-input my_chall.json
2. Format (fmt) Rules to Avoid [H] and [J] Rejections
- Always start with an approved base string (see
references/fmt_standards.md). - If an answer has singular/plural ambiguity (e.g.
credentialvscredentials,headervsheaders), you MUST pin the length explicitly:(11글자 / 11 chars). - If
"ci": true, the hash issha256(answer.strip().toLowerCase()). Never includeFLAG{...}infmtwhenciis enabled.
What ships with it
4 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 · 91 tokens per session scan A 8cec3b20ab9c
wargame-chall-builder is a skill published in the GitHub repository lsszz2100/VibeHacking (88 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 966 once invoked, about $0.0004 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.
wargame-chall-builder compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wargame-chall-builderlsszz2100/VibeHacking | Skill | 88 | yesterday | MIT | A | 91 | Claude Code, Codex |
| playtest-reportDonchitos/Claude-Code-Game-Studios | Skill | 40k | 8d ago | MIT | A | 20 | Claude Code |
| godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills | Skill | 9.3k | 6d ago | Apache-2.0 | A | 93 | Claude Code |
| motionOpenDCAI/GameFactory-3A | Skill | 1.3k | 3d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| texture-workflowarjun988/blender-skills | Skill | 4.1k | 11d ago | MIT | A | 41 | Claude Code |
| scenario-unreal-gameplayscenario-labs/skills | Skill | 3.9k | yesterday | MIT | A | 121 | Claude Code |
| gamedev-shadersericrisco/rsc-harness | Skill | 630 | today | MIT | A | 102 | Claude Code, Codex |