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 agentmods add skills/walletbeat/walletbeat/wallet-data-collectionnpx skills add walletbeat/walletbeat --skill wallet-data-collectiongit clone --depth 1 https://github.com/walletbeat/walletbeatWrote 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/walletbeat/walletbeat/wallet-data-collection)<a href="https://agentmods.dev/skills/walletbeat/walletbeat/wallet-data-collection"><img src="https://agentmods.dev/badge/skills/walletbeat/walletbeat/wallet-data-collection.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00503 |
| Opus 5 | $0.00019 | $0.00251 |
| Sonnet 5 | $0.00008 | $0.00101 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
wallet-data-collection 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 5d 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.
What it actually says
You are assisting a Walletbeat contributor in classifying a wallet's network traffic data. You will be using the pnpm wallet-data-collection:agent tool for all the subtasks involved in this endeavor.
You will need the following pieces of information upfront:
- A wallet's ID (
walletId), as recorded in Walletbeat. You can list the set of known wallet IDs withpnpm wallet-data-collection:agent list-wallet-ids. - The variant being tested for this wallet (
walletVariant). Some wallets have a desktop, mobile, or browser extension variants. Network traffic analysis is done on a per-variant basis, so you need to know which specific variant you need to be dealing with.
If you do not know these pieces of information, ask the user about it. Once you know, follow the rest of these steps.
- Read the
src/tools/wallet-data-collection/README.mdfile in its entirety. This will explain to you how thepnpm wallet-data-collectiontool works. - Run the
pnpm wallet-data-collection:agent --id=walletId --variant=walletVariant check. This command will be your go-to for answering the question of whether you still have work to do.
If you feel overwhelmed by the sheer amount of tasks in front of you as reported by check, do not panic. Your task is simply to make some progress at all. Simply resolve one issue at a time and move on, until you have processed at least 10 such issues, at which point you may post a debrief of your actions and describe what still remains to be done. Do not classify things in bulk.
If you are unsure about a string's categorization or confused about what to do, you can always ask the user for guidance using the ask_user tool.
IMPORTANT: Throughout this workflow, you must NEVER run pnpm wallet-data-collection. Always run pnpm wallet-data-collection:agent instead.
If a command refuses to run when using pnpm wallet-data-collection:agent, do NOT remove the :agent suffix. Instead, treat it as an indication that you are doing something wrong, and reevaluate what to do according to the workflow.
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.
- 5d ago First seen · 24 lines · 38 tokens per session scan A 464b6c957f10
wallet-data-collection is a skill published in the GitHub repository walletbeat/walletbeat (117 stars, last pushed 5d ago), licensed MIT. It adds 38 tokens to every session and 503 once invoked, about $0.0002 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
kurtosis-ethereum
Run Ethereum multi-client devnets using Kurtosis and the ethpandaops/ethereum-package. Use for spinning up local devnets, syncing public testnets, validating cross-client interop, testing fork transitions, shadowforks, running assertoor checks, debugging CL/EL client interactions, or verifying new feature…
squash-bugbot
Triage unresolved bot review comments on a GitHub PR. Use when asked to run /squash-bugbot or to assess, fix, dismiss, reply to, or resolve bot review feedback.
web3-grep-arsenal
Master grep command arsenal for Web3 smart contract auditing. Use when starting a new protocol scan, before deep code review, or when hunting specific vulnerability classes.
web3-hunt-foundation
Hunter mindset, recon setup, and target scoring for Web3 bug bounty. Use at the START of any new protocol hunt - scoring targets, setting up environment, understanding architecture.
web3-start-here
Master index for the web3 smart contract security knowledge base. Use this to navigate the skill chain. Read files in order — each ends with NEXT.
type-safety
Trigger Pattern Always (Aptos Move) - generic type exploitation - Inject Into Breadth agents, depth-state-trace.