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 goldsky-io/goldsky-agent --skill compose-vrfgit clone --depth 1 https://github.com/goldsky-io/goldsky-agentWrote 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/goldsky-io/goldsky-agent/compose-vrf)<a href="https://agentmods.dev/skills/goldsky-io/goldsky-agent/compose-vrf"><img src="https://agentmods.dev/badge/skills/goldsky-io/goldsky-agent/compose-vrf/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/goldsky-io/goldsky-agent/compose-vrf"><img src="https://agentmods.dev/badge/skills/goldsky-io/goldsky-agent/compose-vrf.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 | $0.00241 | $0.12040 |
| Opus 5 | $0.00120 | $0.06020 |
| Sonnet 5 | $0.00048 | $0.02408 |
| Haiku 4.5 | $0.00024 | $0.01204 |
Grade D, and why
compose-vrf scanned grade D with 3 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
The Compose smart wallet is auto-created at runtime and gas-sponsored on Base Sepolia — never tell the user to create or fund a wallet. On the shared path there is **no fulfiller to set** (the contract is permissionless) Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Edits to `compose.yaml` or source files don't take effect after redeploy.** The local `.compose/` bundle cache is stale. Run `rm -rf .compose/` and redeploy. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **HTTP task (curl)** — the `request_randomness` task exercises the full request → event → fulfill path: 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 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 · 722 lines · 241 tokens per session scan D 8d05959654cd
compose-vrf is a skill published in the GitHub repository goldsky-io/goldsky-agent (12 stars, last pushed 12d ago), with no licence file. It adds 241 tokens to every session and 12,040 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it D with 3 findings (subtle steering, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…