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 sendaifun/skills --skill surfpoolgit clone --depth 1 https://github.com/sendaifun/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/sendaifun/skills/surfpool)<a href="https://agentmods.dev/skills/sendaifun/skills/surfpool"><img src="https://agentmods.dev/badge/skills/sendaifun/skills/surfpool/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/sendaifun/skills/surfpool"><img src="https://agentmods.dev/badge/skills/sendaifun/skills/surfpool.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 | $0.00049 | $0.03019 |
| Opus 5 | $0.00024 | $0.01510 |
| Sonnet 5 | $0.00010 | $0.00604 |
| Haiku 4.5 | $0.00005 | $0.00302 |
Grade C, and why
surfpool scanned grade C with 2 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 9d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sL https://run.surfpool.run/ | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL https://run.surfpool.run/ | bash How it starts
The opening of the file, as written. The whole thing — 518 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Surfpool - Solana Development Environment
The definitive guide for Surfpool - where developers start their Solana journey. A drop-in replacement for solana-test-validator that enables local program simulation using Mainnet accounts fetched just-in-time.
What is Surfpool?
Surfpool is a comprehensive development environment that combines local-first testing with real Mainnet data access:
- Mainnet Forking - Clone accounts, programs, and token balances from Mainnet instantly
- Cheatcodes - Special RPC methods for time travel, balance manipulation, and state control
- Infrastructure as Code - Reproducible, auditable deployments using txtx DSL
- Surfpool Studio - Embedded dashboard with transaction inspection and profiling
- Universal Faucet - Get SOL, USDC, USDT, BONK from a single interface
Key Benefits
| Feature | Description |
|---|---|
| Instant Boot | No 2TB snapshots, runs on Raspberry Pi |
| Lazy Forking | Copy-on-read strategy pulls mainnet data as needed |
| Full Compatibility | Works with solana-cli, Anchor, wallets, explorers |
| Zero Config | Auto-detects Anchor projects and deploys programs |
Statistics
- 460+ GitHub stars
- 100+ forks
- Apache 2.0 license
- Current version: v1.0.0
Installation
Automated Installer (Recommended)
curl -sL https://run.surfpool.run/ | bash
Homebrew (macOS)
brew install txtx/taps/surfpool
From Source
git clone https://github.com/txtx/surfpool.git
cd surfpool
cargo surfpool-install
Docker
docker pull surfpool/surfpool
docker run -p 8899:8899 -p 18488:18488 surfpool/surfpool
Quick Start
Start Local Network
# Start with default configuration
surfpool start
# Start with custom RPC source
surfpool start -u https://api.mainnet-beta.solana.com
# Start without terminal UI
surfpool start --no-tui
# Start with debug logging
surfpool start --debug
Access Points
What ships with it
9 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.
- docs/troubleshooting.md 7.5 KB
- examples/basic/getting-started.ts 6.3 KB runs code
- examples/cheatcodes/state-manipulation.ts 9.7 KB runs code
- examples/iac/deployment.tx 6.8 KB
- resources/cheatcodes.md 10 KB
- resources/cli-reference.md 6.4 KB
- resources/github-repos.md 3.3 KB
- templates/Surfpool.toml 5.5 KB
- templates/test-setup.ts 9.4 KB runs code
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.
- 9d ago First seen · 518 lines · 49 tokens per session scan C feafb851366e
surfpool is a skill published in the GitHub repository sendaifun/skills (128 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 3,019 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, 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
foundry-solidity
Build and test Solidity smart contracts with Foundry toolkit. Use when developing Ethereum contracts, writing Forge tests, deploying with scripts, or debugging with Cast/Anvil. Triggers on Foundry commands (forge, cast, anvil), Solidity testing, smart contract development, or files like foundry.toml, .t.sol, .s.sol.
offensive-fuzzing
Practical offensive fuzzing methodology covering target identification, fuzzer selection (AFL++, libFuzzer, Honggfuzz, Boofuzz, syzkaller), harness writing, corpus curation, mutation strategies, coverage measurement, and crash triage. Use when setting up or running fuzz campaigns against any target: file parsers…
offensive-business-logic
Business logic vulnerability testing for web/mobile/API engagements. Covers workflow bypass, state machine violations, multi-step process abuse, price/quantity/discount manipulation, currency confusion, coupon stacking, refund/chargeback abuse, race conditions on logic boundaries, parameter tampering for hidden flows…
review-ugc-render
Mandatory pre-publish review gate for a UGC video render. Transcribes the finished render's AUDIO with Whisper and word-diffs it against the approved spoken script, then gates setfinalrender — blocking a render whose generated audio mis-voices a word (e.g. the approved "human-vetted" spoken as "human witted"), drops…
api-tester
Test and document API endpoints - validate responses, check status, generate examples.
offensive-race-condition
Race condition (TOCTOU) testing checklist: identifying timing windows, Burp Suite Turbo Intruder, Last-Byte sync technique, rate limit bypass, double-spend attacks, and concurrent request exploitation. Use for web app race condition testing or bug bounty time-of-check-to-time-of-use bugs.