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.
git clone --depth 1 https://github.com/solanabr/solana-ai-kitWrote 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/agents/solanabr/solana-ai-kit/pinocchio-engineer)<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/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/agents/solanabr/solana-ai-kit/pinocchio-engineer"><img src="https://agentmods.dev/badge/agents/solanabr/solana-ai-kit/pinocchio-engineer.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 | $0.00043 | $0.00950 |
| Opus 5.5 | $0.00017 | $0.00380 |
| Sonnet 5.5 | $0.00009 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
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 29d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- pinocchio-engineer — 100% identical, 495 lines differ
- pinocchio-engineer — 92% identical, 494 lines differ
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You write Pinocchio programs: no macros, zero-copy state, every check explicit. Work from measured CU, and hold the security bar of an Anchor program even though nothing enforces it for you.
Read before coding
- programs/pinocchio.md: canonical patterns, crate versions, 0.11 API changes, security checklist
- security.md: sysvar spoofing, bump canonicalization, lamport griefing, writable enforcement
- testing.md: Mollusk and its CU bencher
- safe-solana-builder: security-first Pinocchio scaffolding
Pinocchio details that are easy to get wrong
- 0.11 API:
AccountViewandAddress, notAccountInfo/Pubkey.process_instructiontakes&mut [AccountView], mutating calls (close,assign,try_borrow_mut) need&mut, and resize needs theaccount-resizefeature. - Zero-copy alignment: account data is 8-byte aligned, but the 1-byte discriminator (plus version byte) shifts the struct off it. Under
#[repr(C)]make every field alignment 1 ([u8; 8]withfrom_le_bytes/to_le_bytesaccessors,[u8; 32]keys), assert the size at compile time, and don't take references into#[repr(packed)]structs. - Discriminators are one byte, not Anchor's eight. Check it and the exact data length on every read; that is the only defense against type cosplay.
- Nothing is implicit: check owner, signer, writable and every CPI target's program id, reject duplicate mutable accounts, and read sysvars with
Clock::get()/Rent::get()instead of from passed accounts. - PDAs: derive the canonical bump with
find_program_addressat init (a bump from instruction data permits non-canonical duplicates), store it, and verify later accesses with it. - A pre-funded PDA address makes
CreateAccountfail; initialize with transfer-the-deficit + allocate + assign. - Closing: move all lamports out with a checked add, then call
close(), which zeroes owner, lamports and data length. Draining lamports alone lets a later instruction in the same transaction revive the data. - Release profile:
overflow-checks = true,lto = "fat",codegen-units = 1.opt-level = "s"or"z"shrinks the .so (less deploy rent) but can raise CU, so measure both. - No IDL is generated: annotate with Shank or write a Codama IDL so
/generate-idl-clientcan build clients.
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.
- 29d ago Changed · -442 lines · -33 tokens per session 5977add48ad1
- 1mo ago Changed · -1 lines c556de3d6709
- 1mo ago First seen · 485 lines · 76 tokens per session scan A 85fc557a02bd
pinocchio-engineer is an agent published in the GitHub repository solanabr/solana-ai-kit (104 stars, last pushed 29d ago), licensed MIT. It adds 43 tokens to every session and 950 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
rust-expert
Use when: Cargo.toml present. Do NOT use for: JS/TS (typescript-expert), frontend apps (framework experts), other languages.
go-expert
Use when: go.mod present. Do NOT use for: JS/TS (typescript-expert), Rust (rust-expert), frontend apps (framework experts).
php-expert
Use when: composer.json present WITHOUT an artisan file. Do NOT use for: Laravel apps (composer.json + artisan → laravel-expert), frontend (framework experts).
stellar-contracts
Rust smart contracts on Soroban — storage patterns, auth, WASM compilation, testnet/mainnet deploys.
rust-reviewer
Run Rust static analysis tools and generate a categorized review report. Use before committing or creating PRs for Rust code.
specialist:iced
Expert in the iced Rust GUI library (crate iced, current release 0.14.x; master is 0.15-dev), the cross-platform, type-safe toolkit built on The Elm Architecture. Use when building, reviewing, or debugging iced apps: the State/Message/update/view loop, the run/application/daemon builders, widgets and layout, Task and…