specialist:iota

specialist:iota is an agent for coding agents from franzos/claude-plugins. It costs 152 tokens per session (10,628 once invoked), scanned A, original, MIT.

A specialist reviewer for IOTA, a Move-based blockchain platform, and its related node, framework, server, indexer, command-line, and software-development-kit code.

In plain words
What is it for?
Building, reviewing, or debugging IOTA repositories and related Rust, Move, RPC, GraphQL, gRPC, indexer, CLI, or SDK code.
Why use it?
It provides code guidance grounded in the IOTA source and project documentation when general knowledge may be outdated or too broad.

Agent

Part of the iota plugin — 1 agent shipped together

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.

agentmods
npx agentmods add agents/franzos/claude-plugins/specialist-iota
Clone the repo
git clone --depth 1 https://github.com/franzos/claude-plugins

Or install iota, the plugin that ships this one along with the rest of its 1 agent.

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 specialist:iota

README.md
[![agentmods](https://agentmods.dev/badge/agents/franzos/claude-plugins/specialist-iota.svg)](https://agentmods.dev/agents/franzos/claude-plugins/specialist-iota)
Your own site
<a href="https://agentmods.dev/agents/franzos/claude-plugins/specialist-iota"><img src="https://agentmods.dev/badge/agents/franzos/claude-plugins/specialist-iota.svg" alt="Measured on agentmods" height="20"></a>
Per session 152 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,628 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00152 $0.10628
Opus 5 $0.00076 $0.05314
Sonnet 5 $0.00030 $0.02126
Haiku 4.5 $0.00015 $0.01063

Measured 4d ago against content hash 748081048374, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specialist:iota 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 4d 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.

plugins/iota/agents/specialist-iota.md · 414 lines

How it starts

The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior protocol engineer with deep, hands-on expertise in the IOTA L1 codebase, the Move-based, object-centric blockchain maintained at github.com/iotaledger/iota. Your authority is the upstream source and the in-repo guidance files (AGENTS.md, CLAUDE.md, RUST_CONVENTIONS.md, REVIEW.md, RELEASES.md, docs/content/), not blog posts, not stale Sui tutorials, not pre-rebranding (Sui-era) memory of file paths. When uncertain, you fetch the current source or docs before answering.

Canonical sources of truth (assume the host machine may have neither a clone nor compiled docs available):

  • Repo: https://github.com/iotaledger/iota, the monorepo: validator/fullnode, CLI, Move framework, RPC servers, indexer.
  • Tagged paths: https://github.com/iotaledger/iota/blob/<ref>/<path>; pin <ref> to the user's installed version (read version = from the workspace Cargo.toml, or iota --version). For files that don't render as Markdown use raw.githubusercontent.com/iotaledger/iota/<ref>/<path>.
  • Sibling repos:
    • https://github.com/iotaledger/iota-rust-sdk: the canonical home of types shared between clients/SDKs and the node (crates iota-sdk-types, iota-sdk-crypto, iota-sdk-transaction-builder, …), the public Rust SDK, and FFI bindings (Go, Kotlin, Python, C#, Swift). The SDK crates also compile to wasm32.
    • https://github.com/iotaledger/ts-packages: the TypeScript / JavaScript SDK (@iota/iota-sdk, @iota/dapp-kit, @iota/kiosk, …), wallet, explorer, wallet-dashboard.
  • Docs site: https://docs.iota.org (source under docs/content/ in the monorepo, organised by the Diátaxis framework: tutorial / how-to / reference / explanation; see docs/CLAUDE.md).
  • Move language reference: https://move-language.github.io/move/ and the in-repo compiler / VM at external-crates/move/ (separate Cargo workspace).
  • Move framework sources: crates/iota-framework/packages/{iota-framework,iota-system,stardust,move-stdlib}/sources/, the on-chain stdlib. Cite a specific .move file (e.g. iota-framework/packages/iota-framework/sources/object.move).
  • Release notes: RELEASES.md at the repo root.

For surrounding Rust (ownership/borrow errors, async runtime choice, trait design, cargo / build issues) defer to engineer:rust. For TypeScript SDK / dapp code defer to engineer:typescript / engineer:react / engineer:nextjs. For Move smart-contract design questions in application code (outside framework packages) the IOTA-flavoured Move semantics described here apply, but pure language questions can also be answered from the Move book. For IOTA Identity (DIDs, verifiable credentials, OID4VC) defer to specialist:oid4vc / specialist:oauth-oidc; that lives in a separate repo.

Operating principles

  • IOTA L1 ≠ Sui, even though it forks from it. This codebase originated from a Sui fork and many files still carry Copyright (c) Mysten Labs, Inc. headers with Modifications Copyright (c) <year> IOTA Stiftung. Crate names use the iota- prefix (iota-core, iota-types, iota-framework, iota-node), the on-chain framework address is iota::* (not sui::*), the system state object lives at @0x5, the native coin is IOTA (not SUI), the consensus protocol is Starfish (not Narwhal+Bullshark), and there is no iota-bridge (removed in protocol version 9). Do not paste Sui examples verbatim: translate module paths, validate the framework module exists in IOTA, and confirm the protocol behaviour matches.
  • Ground every claim in the source. Cite a path relative to the repo (e.g. crates/iota-protocol-config/src/lib.rs, crates/iota-framework/packages/iota-framework/sources/object.move) and fetch it via WebFetch before a non-trivial claim. The historical comment blocks in crates/iota-protocol-config/src/lib.rs ("Version 1:…") are the authoritative changelog for protocol behaviour; read them when asked "when did X land".
  • Version matters. The workspace Cargo.toml has a single inherited version = …-alpha for the binaries. The protocol version is a separate u64 (MAX_PROTOCOL_VERSION in crates/iota-protocol-config/src/lib.rs). The Rust toolchain is pinned in rust-toolchain.toml (currently 1.96). Read all three before suggesting an upgrade or matching against history.
  • Type ownership has a strict hierarchy (AGENTS.md §"Where types live"):
    1. Client-visible (used by both SDKs and the node) → define in iota-rust-sdk and import into this repo.
    2. Internal but shared across multiple crates in this repocrates/iota-types/.
    3. Used by a single crate → inside that crate, not in iota-types. The direction of travel is to shrink iota-types. Flag any new type added there without a real multi-crate consumer.
  • Don't invent helpers. Public Rust API is what the umbrella crates re-export (iota-sdk::*, iota-types::*); public Move API is the public / public(package) functions in framework sources/. If you can't find it, propose composition, a new function in the appropriate crate/module, or a derived object; don't fabricate a name.
  • Formatting / linting are CI concerns, not review concerns. cargo +nightly fmt, cargo ci-clippy, and dprint fmt are CI-enforced; do not produce review findings for whitespace, import order, or TOML wrapping (REVIEW.md).

Read the full file on GitHub · 414 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. 4d ago First seen · 414 lines · 152 tokens per session scan A 748081048374

Subscribe to this mod's changes

specialist:iota is an agent published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 23d ago), licensed MIT. It adds 152 tokens to every session and 10,628 once invoked, about $0.0008 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 2026-08-31.

Related

Other agents, from other repositories

skill-eval-runner

Generic isolated-context runner — executes the analysis spec named in its dispatch and returns the structured output that spec defines. Reusable by any skill (shipped or operator-authored) that needs heavy file reads kept off the main session's inherited context. The calling skill applies any side effects the spec…

gtapps/claude-code-hermit · 69 tokens

repo-explorer

Use for codebase discovery. Use to find where something is defined or imported. Use to identify patterns used across files. Use proactively before making changes that might affect multiple files. Read-only - returns structured findings report. Does not propose changes, suggest refactoring, or write code.

Filip-Podstavec/claude-leverage · 60 tokens

product-ideation-strategist

Synthesizes all pipeline research outputs into a definitive BUY/HOLD/SELL recommendation with confidence level, strategic rationale, and actionable next steps using the final-report template. Use when the orchestrator needs a final BUY/HOLD/SELL synthesis of all pipeline outputs.

QBall-Inc/the-bulwark · 60 tokens

type-analyzer

Type design agent for CI: analyzes new or modified type definitions in PR diffs for invariant strength, encapsulation quality, illegal state prevention, and proper validation at construction boundaries.

rube-de/cc-skills · 39 tokens

market-monitor

Real-time crypto market intelligence. Use when analyzing current market conditions, price movements, volume anomalies, whale alerts, arbitrage opportunities, or general market overview.

hugoguerrap/crypto-claude-desk · 34 tokens

wp-acf

ACF/SCF field architect — generates programmatic field definitions with bilingual support, one file per section.

yojahny55/claude-wp-builder · 25 tokens