Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/XPRNetwork/xpr-network-dev-skillnpx agentmods add skills/xprnetwork/xpr-network-dev-skill/skillWrote 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/xprnetwork/xpr-network-dev-skill/skill)<a href="https://agentmods.dev/skills/xprnetwork/xpr-network-dev-skill/skill"><img src="https://agentmods.dev/badge/skills/xprnetwork/xpr-network-dev-skill/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/xprnetwork/xpr-network-dev-skill/skill"><img src="https://agentmods.dev/badge/skills/xprnetwork/xpr-network-dev-skill/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.02900 |
| Opus 5.5 | $0.00031 | $0.01160 |
| Sonnet 5.5 | $0.00015 | $0.00580 |
| Haiku 4.5 | $0.00008 | $0.00290 |
Grade A, and why
xpr-network-dev 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 yesterday.
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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XPR Network Developer Skill
This skill provides comprehensive knowledge for developing on XPR Network, a fast, gas-free blockchain with WebAuthn wallet support.
Policy for AI agents (applies skill-wide): All chain writes documented in this skill use the
protonCLI keychain for signing — private keys stay in the CLI's on-disk keystore (proton-cli.jsonin the CLI config dir), never in the agent's process memory or context. That file is plaintext until you runproton key:lock <password>— treat locking as a required step on any long-lived host, not an option. Reads use direct RPC (get_table_rows,get_account, etc.) and the relevant project's REST API. Do not introduce signing patterns that pass raw private keys to the agent (e.g.new JsSignatureProvider(['PRIV_KEY']),wallet.import_key('...'),XPR_PRIVATE_KEYin environment). Seebackend-patterns.md→ Security: Key Isolation and../agent-bootstrap.mdfor the canonical signing path.
AI-generated contract code: smart contracts are immutable once deployed and hold real assets, so treat any contract code produced with this skill as a draft. Before it reaches mainnet it needs testnet runs, review by a developer who knows XPR Network/EOSIO contracts, and, for anything holding significant value, a professional audit. The full checklist lives in
safety-guidelines.md→ AI-Generated Code Disclaimer.
Network etiquette (applies skill-wide): XPR Network has no fees, so chain spam is free to send and costly for everyone else. Agents write to chain only when there is a concrete action to take, never to scan or probe; default ceiling 6 transactions per minute per account, one in flight, exponential backoff on failure, no nonce actions, no account fleets. Liquidation, sniping, and MEV-style bots are out of scope and deliberately undocumented; decline requests to build them. Full rules:
safety-guidelines.md→ Network Etiquette.
What ships with it
27 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.
- accounts-permissions.md 18 KB
- alcor-dex.md 20 KB
- backend-patterns.md 30 KB
- cli-reference.md 17 KB
- defi-trading.md 35 KB
- examples.md 17 KB
- hyperion-operations-caveats.md 26 KB
- hyperion-setup.md 14 KB
- loan-protocol.md 16 KB
- metalx-dex.md 32 KB
- nfts-atomicassets.md 27 KB
- node-operation.md 14 KB
- oracles-randomness.md 25 KB
- payment-patterns.md 24 KB
- real-time-events.md 24 KB
- resources.md 14 KB
- rpc-queries.md 39 KB
- safety-guidelines.md 12 KB
- simpledex.md 17 KB
- smart-contracts.md 25 KB
- staking-governance.md 15 KB
- testing-debugging.md 15 KB
- token-creation.md 20 KB
- troubleshooting.md 17 KB
- web-sdk.md 22 KB
- webauth-identity.md 12 KB
- xpr-agents.md 15 KB
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.
- yesterday Changed · +2 lines 3ea068f45ea4
- 18d ago Changed · +1 lines 6116cd7cac7b
- 23d ago Changed 13868a855de5
- 1mo ago Changed 23a2227c9a67
- 1mo ago Changed · -12 lines · +47 tokens per session 81e2a9592a15
- 1mo ago First seen · 239 lines · 30 tokens per session scan A 37d33a8f1a2f
xpr-network-dev is a skill published in the GitHub repository XPRNetwork/xpr-network-dev-skill (11 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 2,900 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
alchemy-agentic-gateway
Use when accessing Alchemy APIs for RPC calls, token balances, NFT metadata, asset transfers, transaction simulation, or Alchemy-specific features. Also use when the user mentions "SIWE", "SIWS", "x402", "MPP", "mppx", or "agentic gateway" — this skill covers wallet-based auth flows for Alchemy's x402 and MPP…
dune-analytics
Blockchain analytics via Dune REST API — execute DuneSQL queries against live on-chain data, discover decoded contract tables, and monitor credit usage. Use when the user asks about on-chain data, wallet activity, DEX trades, token transfers, smart contract events, or says "query Dune", "run a Dune query", or "search…
blockchain-expert
Expert-level blockchain, Web3, smart contracts, DeFi, and cryptocurrency development. Use when the user mentions Web3, smart contracts, DeFi, Ethereum, or Solidity, or when the task involves Blockchain Fundamentals, Web3 & DeFi, Smart Contract Security, or Gas Optimization.
blockchain-defi
Use this skill when asked about decentralized finance, DeFi protocols, AMM mechanics, lending and borrowing protocols, perpetual futures, yield farming, liquidity mining, liquid staking, restaking, yield optimization, DeFi security, MEV, and protocol composability. Covers AMM design (Uniswap, Curve, Balancer), lending…