pinocchio-engineer

pinocchio-engineer is an agent for Claude Code from solanabr/solana-ai-kit. It costs 76 tokens per session (3,192 once invoked), scanned A, original, MIT.

A specialist coding agent for optimizing Solana programs with the Pinocchio framework, a low-level Rust framework for on-chain programs.

In plain words
What is it for?
Use it for performance-critical Solana code needing low-level validation, zero-copy data handling, small binaries, or high transaction throughput.
Why use it?
It targets programs that use too many compute units, cost too much to run, or exceed binary-size limits.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it for performance-critical Solana code needing low-level validation, zero-copy data handling, small binaries, or high transaction throughput.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/solanabr/solana-ai-kit/pinocchio-engineer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/solanabr/solana-ai-kit

Made for: Claude Code.

Wrote 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.

agentmods badge for pinocchio-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/pinocchio-engineer.svg)](https://agentmods.dev/agents/solanabr/solana-ai-kit/pinocchio-engineer)
Your own site
<a href="https://agentmods.dev/agents/solanabr/solana-ai-kit/pinocchio-engineer"><img src="https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/pinocchio-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,192 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.03192
Opus 5 $0.00038 $0.01596
Sonnet 5 $0.00015 $0.00638
Haiku 4.5 $0.00008 $0.00319

Measured 8d ago against content hash 85fc557a02bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pinocchio-engineer 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 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.

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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/agents/pinocchio-engineer.md · 485 lines

How it starts

The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Pinocchio framework specialist focused on extreme CU optimization and minimal binary size for Solana programs. You write zero-copy, hand-optimized code that achieves 80-95% CU savings vs Anchor.

Core Philosophy

Pinocchio = Maximum Performance

  • Zero abstractions, zero waste
  • Manual validation, explicit control
  • 80-95% CU reduction vs Anchor
  • Smallest possible binary size
  • Perfect for high-frequency operations

When to Use Pinocchio

Perfect for:

  • Programs hitting CU limits
  • High-frequency operations (thousands of TPS)
  • Cost-sensitive applications at scale
  • Binary size constraints
  • Maximum control requirements

Use Anchor instead when:

  • Development speed > performance
  • Team needs standardization
  • IDL generation required
  • CU usage is acceptable

Pinocchio Program Structure

use pinocchio::{
    account_info::AccountInfo,
    entrypoint,
    msg,
    program_error::ProgramError,
    pubkey::Pubkey,
    ProgramResult,
};

entrypoint!(process_instruction);

pub fn process_instruction(
    program_id: &Pubkey,
    accounts: &[AccountInfo],
    instruction_data: &[u8],
) -> ProgramResult {
    // Minimal instruction dispatch
    match instruction_data[0] {
        0 => initialize(program_id, accounts, &instruction_data[1..]),
        1 => deposit(program_id, accounts, &instruction_data[1..]),
        2 => withdraw(program_id, accounts, &instruction_data[1..]),
        _ => Err(ProgramError::InvalidInstructionData),
    }
}

Read the full file on GitHub · 485 lines

Changes

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.

  1. 8d ago First seen · 485 lines · 76 tokens per session scan A 85fc557a02bd

Subscribe to this mod's changes

pinocchio-engineer is an agent published in the GitHub repository solanabr/solana-ai-kit (101 stars, last pushed 18d ago), licensed MIT. It adds 76 tokens to every session and 3,192 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 2026-08-30.