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 ObolNetwork/obol-stack --skill inspectgit clone --depth 1 https://github.com/ObolNetwork/obol-stackWrote 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/obolnetwork/obol-stack/inspect)<a href="https://agentmods.dev/skills/obolnetwork/obol-stack/inspect"><img src="https://agentmods.dev/badge/skills/obolnetwork/obol-stack/inspect/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/obolnetwork/obol-stack/inspect"><img src="https://agentmods.dev/badge/skills/obolnetwork/obol-stack/inspect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00107 | $0.02311 |
| Opus 5.5 | $0.00043 | $0.00924 |
| Sonnet 5.5 | $0.00021 | $0.00462 |
| Haiku 4.5 | $0.00011 | $0.00231 |
Grade A, and why
inspect scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
metadata: { "openclaw": { "emoji": "🔎", "requires": { "bins": ["python3", "cast", "curl"] } } } How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspect
Decode before you sign. Vet before you pay. Two read-only tools for the moment right before money or authority leaves the wallet:
scripts/decode.py— what does this calldata / transaction DO?scripts/contract.py— who or what is this address, really?
When to Use
- About to sign unfamiliar calldata or an EIP-712 payload (e.g. the Permit2
approval printed by
buy-x402) —decode.py calldata - Reviewing a transaction someone sent, or auditing one you already sent —
decode.py tx <hash> - About to pay a new or unknown x402 seller —
contract.py check <payTo> - Vetting a counterparty token or contract before approving/holding it —
contract.py check <token>(source verified? proxy? labeled?) - Deciding whether an address is a wallet or code —
contract.py code(detects EIP-7702 delegated EOAs) - Turning an ENS/Basename into an address (or back) —
contract.py resolve
When NOT to Use
- Making the actual payment — use
buy-x402 - Generic RPC reads (balances, blocks, logs) — use
ethereum-networks - Signing or sending transactions — use
ethereum-local-wallet - Discovering sellers on the ERC-8004 registry — use
discovery
Quick Start
# What am I about to sign? (ERC-20 selectors decode fully offline)
python3 ${OBOL_SKILLS_DIR:-/data/.hermes/obol-skills}/inspect/scripts/decode.py calldata \
0xa9059cbb000000000000000000000000ab5801a7d398351b8be11c439e05c5b3259aec9b00000000000000000000000000000000000000000000000000000000000f4240
# selector: 0xa9059cbb
# function: transfer(address,uint256)
# address: 0xAb5801a7D398351b8bE11C439e05C5B3259aeC9B
# uint256: 1000000 [1e6]
# Who am I about to pay? Composite due-diligence on the payTo address.
python3 ${OBOL_SKILLS_DIR:-/data/.hermes/obol-skills}/inspect/scripts/contract.py check \
0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48 --network mainnet
# -> code / proxy / verified source / labels / ENS+Basename sections
# What did this transaction do?
python3 ${OBOL_SKILLS_DIR:-/data/.hermes/obol-skills}/inspect/scripts/decode.py tx \
0xa2b4273e... --network mainnet
What ships with it
3 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.
- 8d ago Changed 2e335a987cf2
- 1mo ago First seen · 157 lines · 107 tokens per session scan A e41cf969e975
inspect is a skill published in the GitHub repository ObolNetwork/obol-stack (11 stars, last pushed today), licensed Apache-2.0. It adds 107 tokens to every session and 2,311 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (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
ethereum-development
Production-grade Ethereum/EVM development workflow for smart contracts, dApps, transactions, clients, gas optimization, testing, security review, deployment, verification, monitoring, and incident response across Foundry, Hardhat, Solidity, TypeScript, viem, ethers, wagmi, and common EVM networks.
Web3 & Blockchain Development
Production-grade Web3 development with Solidity smart contracts, ethers.js/web3.js integration, DApp architecture, security patterns, and AI-enhanced blockchain development (ChatWeb3, Aider + Gemini 2024).
pump-swarm
Coordinated multi-wallet trading on Pump.fun.
trading-solana
Trade tokens on Solana DEXes - Jupiter, Raydium, Orca, Meteora, Pump.fun.
public
For agents: This document explains how to integrate with Clodds APIs.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).