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 x402agent/solana-clawd --skill ultrathink-blockchaingit clone --depth 1 https://github.com/x402agent/solana-clawdWrote 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/x402agent/solana-clawd/ultrathink-blockchain)<a href="https://agentmods.dev/skills/x402agent/solana-clawd/ultrathink-blockchain"><img src="https://agentmods.dev/badge/skills/x402agent/solana-clawd/ultrathink-blockchain/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/x402agent/solana-clawd/ultrathink-blockchain"><img src="https://agentmods.dev/badge/skills/x402agent/solana-clawd/ultrathink-blockchain.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 | $0.00076 | $0.01558 |
| Opus 5 | $0.00038 | $0.00779 |
| Sonnet 5 | $0.00015 | $0.00312 |
| Haiku 4.5 | $0.00008 | $0.00156 |
Grade A, and why
ultrathink-blockchain 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ultrathink Blockchain
A Claude Code skill for building production Solana systems with deep reasoning.
Activation
This skill activates when the user is working on blockchain development — specifically Solana — and needs production-quality code with proper transaction handling, MEV protection, and failure resilience.
Trigger phrases: blockchain, solana, on-chain, web3, defi, token, swap, sniper, anchor, program, transaction, RPC, Helius, Jito, MEV, PDA
Protocol
When this skill is active, follow the Ultrathink Blockchain Formula:
Phase 1: Context Dump
Before writing any blockchain code, establish the environment:
Context: [chain] [network: mainnet/devnet/testnet]
Stack:
- Runtime: [Node.js/Bun + TypeScript | Rust/Anchor]
- RPC: [Helius/Quicknode/Triton + features used]
- Data: [Birdeye/Jupiter/on-chain reads]
- Execution: [Jito bundles / standard RPC / both]
- Wallet: [Keypair from env / browser wallet / multisig]
Constraints:
- Transactions must land in 1-2 slots or fail fast
- All RPC calls need retry logic with exponential backoff
- Assume network is adversarial (MEV, failed txs, RPC lag)
- Compute units are precious — simulate before send
- Every transaction needs priority fee estimation
If the user hasn't provided this context, ask for it before writing code. This prevents generic web2 patterns from leaking in.
Phase 2: Intent Declaration
Ensure the goal is dimensional, not vague:
- Bad: "Build me a swap"
- Good: "Build a Jupiter swap executor that handles multi-hop routes with <200ms latency, uses Jito for MEV protection, and retries with fresh blockhash on failure"
If the user's intent is vague, help them make it specific by asking about success criteria, latency requirements, and failure tolerance.
Phase 3: Extraction Interview
Before writing code, extract requirements through structured questioning. Ask 3-5 questions at a time covering:
Architecture:
- Client-side (TypeScript) or on-chain program (Rust/Anchor)?
- What programs/accounts does this interact with?
- Deploy new contracts or call existing?
What ships with it
11 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.
- CONTRIBUTING.md 2.2 KB
- docs/blockchain-patterns.md 5.9 KB
- docs/depth-ladder.md 3.0 KB
- docs/formula.md 10 KB
- LICENSE 1.1 KB
- README.md 7.2 KB
- references/antipatterns.md 5.0 KB
- references/templates.md 6.1 KB
- site/index.html 24 KB
- ultrathink-blockchain-formula.md 19 KB
- ultrathink-blockchain.skill 9.5 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.
- 7d ago First seen · 209 lines · 76 tokens per session scan A 905fc86b8375
ultrathink-blockchain is a skill published in the GitHub repository x402agent/solana-clawd (24 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 1,558 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
solana
Use when working on Solana software, including one or more of: Solana client code using TypeScript, Rust libraries that use Solana crates, Anchor programs, Quasar programs, LiteSVM tests, including Rust program files, TypeScript tests, and Anchor.toml or Quasar.toml configuration. Designed to create minimal, reusable…
solana-toolkit-guide
Guide to the Solana Wallet Toolkit — vanity address generation with multi-threaded search, official Solana Labs libraries, Rust and TypeScript implementations. Includes wallet generation, custom address prefixes, and OG names on the blockchain.
atproto-cid
This skill should be used when the user is working with AT Protocol or DASL CIDs (Content Identifiers) in Rust, TypeScript, or Go — parsing, constructing, validating, verifying, or debugging them. Triggers on phrases like "parse a CID", "compute a CID for this record", "verify a blob CID", "why is this CID invalid"…
ax-rust-llm
Use when writing Rust code with axllm for using the generated Ax package, factory functions, package docs, examples, and API reference.
ax-rust-signature
Use when writing Rust code with axllm for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.