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 drpcorg/drpc-agent-skills --skill drpc-rpc-pigit clone --depth 1 https://github.com/drpcorg/drpc-agent-skillsWrote 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/drpcorg/drpc-agent-skills/drpc-rpc-pi)<a href="https://agentmods.dev/skills/drpcorg/drpc-agent-skills/drpc-rpc-pi"><img src="https://agentmods.dev/badge/skills/drpcorg/drpc-agent-skills/drpc-rpc-pi/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/drpcorg/drpc-agent-skills/drpc-rpc-pi"><img src="https://agentmods.dev/badge/skills/drpcorg/drpc-agent-skills/drpc-rpc-pi.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 | $0.00060 | $0.00474 |
| Opus 5 | $0.00030 | $0.00237 |
| Sonnet 5 | $0.00012 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
drpc-rpc-pi 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 10d 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
DRPC RPC — Pi Agent Setup Overlay
This skill is Pi Agent-specific. Generic DRPC RPC behavior lives in skills/drpc-rpc/.
Scope
Use this overlay only in Pi Agent, when this repository is installed as a Pi package with its extension loaded.
The Pi extension provides:
drpc_setup— agent-callable tool:- without
apiKey: installs/configures Coinbase Payments MCP for secure x402 bootstrap - with
apiKey: configures DRPC MCP in~/.pi/agent/mcp.json
- without
drpc_coinbase_wallet_setup— agent-callable tool to install/configure Coinbase Payments MCP/drpc-setup— manual DRPC API-key setup command/drpc-coinbase-wallet-setup— manual Coinbase Payments MCP setup command
Pi Flow When DRPC MCP Is Missing
- Check the MCP server list.
- If DRPC MCP is unavailable but
drpc_setupexists, calldrpc_setupwith noapiKey.- The Pi extension installs the Coinbase Payments MCP bundle if missing.
- It writes/updates
~/.pi/agent/mcp.jsonforpayments-mcp.
- Re-check the MCP server list.
- If
payments-mcpis still not visible, tell the user that the Pi/MCP session must reload or restart to pick up the newly written MCP server. - Once
payments-mcpis visible, use it to acquire a DRPC API key via x402. - Call
drpc_setupagain with the acquired DRPC API key. - Re-check DRPC MCP. If it is still unavailable in the current session, execute the current request using the generic direct HTTP fallback from
skills/drpc-rpc/direct-http.md.
Do not ask the user for private keys in Pi. Prefer Coinbase Agentic Wallet / Payments MCP for x402 so wallet custody stays outside Pi.
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.
- 10d ago First seen · 36 lines · 60 tokens per session scan A 0054e8333283
drpc-rpc-pi is a skill published in the GitHub repository drpcorg/drpc-agent-skills (23 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 474 once invoked, about $0.0003 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
aelf-node-skill
AElf node querying and contract execution skill for agents.
Smart Contract Testing
Smart contract testing with Hardhat, Foundry, and Brownie including unit tests, gas optimization, reentrancy checks, and fork testing.
animica-chain
Query the Animica L1 blockchain over JSON-RPC or explorer REST. Use when you need the chain head, an account balance, a transaction, a block, forks, hashrate, or any other on-chain Animica data.
animica-payments
Check ANM balances and run merchant payment flows (create payment intents, poll status, verify webhooks) via the Animica Pay API at pay.animica.dev. Use when accepting ANM payments, integrating a checkout, reconciling payments, or reading an account's ANM balance.
animica-explorer
Inspect Animica blocks, transactions, addresses, mempool, richlist, supply, and the L2 rollup via the free explorer REST API. Use when you need indexed/enriched chain data (confirmations, tx classification, address history) rather than raw node RPC.
animica-mining
Join the Animica mining pool (stratum endpoints, CLI quickstart) and read pool statistics via the pool REST API. Use when setting up a miner, checking pool/network hashrate, listing miners, or looking up recent blocks and payouts.