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 lxyeternal/MalSkillBench --skill agent-arena-skillgit clone --depth 1 https://github.com/lxyeternal/MalSkillBenchWrote 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/lxyeternal/malskillbench/agent-arena-skill)<a href="https://agentmods.dev/skills/lxyeternal/malskillbench/agent-arena-skill"><img src="https://agentmods.dev/badge/skills/lxyeternal/malskillbench/agent-arena-skill/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/lxyeternal/malskillbench/agent-arena-skill"><img src="https://agentmods.dev/badge/skills/lxyeternal/malskillbench/agent-arena-skill.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 | $0.00078 | $0.09585 |
| Opus 5 | $0.00039 | $0.04792 |
| Sonnet 5 | $0.00016 | $0.01917 |
| Haiku 4.5 | $0.00008 | $0.00958 |
Grade A, and why
agent-registry 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 6d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
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.
- 6d ago First seen · 1,030 lines · 78 tokens per session scan A e4c7e7bda34a
agent-registry is a skill published in the GitHub repository lxyeternal/MalSkillBench (59 stars, last pushed 3mo ago), with no licence file. It adds 78 tokens to every session and 9,585 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 2026-09-03.
Other skills, from other repositories
trustlayer-sybil-scanner
Feedback forensics for ERC-8004 agents. Detects Sybil rings, fake reviews, rating manipulation, and reputation laundering across 20 chains. No API key needed.
x402
HTTP 402 payment protocol for AI agent commerce — three-actor model (Client, Resource Server, Facilitator), ERC-3009 transferWithAuthorization, server middleware (@x402/express), client patterns in TypeScript and Python, facilitator integration, agent-to-agent payments, pricing strategies, and replay protection. Works…
x402-server
Add x402 payment protection to any API endpoint using @dexterai/x402/server. Trigger when the user wants to monetize an API, add a paywall, accept crypto payments on their server, set up Stripe settlement, configure dynamic pricing, create access passes, or enable sponsored access (ads for agents).
x402-client
Integrate one-shot x402 payments into a Node.js or browser application with @dexterai/x402/client. Trigger when the user wants to call a paid API, use payAndFetch, create application-owned wallets, set spending limits, inspect receipts, or handle sponsored recommendations.
x402-discoverable
Get an x402 API discovered and listed on the OpenDexter / x402gle catalog so paying agents can find it. Trigger when the user has an x402 API and wants it listed, indexed, discoverable, or found by agents; wants to onboard or register a paid endpoint; asks how agents will find their API; or mentions opendexter…
swarmdock
SwarmDock marketplace integration — register on the P2P agent marketplace, discover paid tasks, bid competitively, complete work, and earn USDC. Includes event-driven agent mode, reputation tracking, portfolio management, and dispute resolution. Use when an agent needs to find paid work, monetize skills, or interact…