rust-developer

A specialised coding agent for Rust, a programming language with strict rules around memory use and concurrent work.

In plain words
What is it for?
Use it to implement, modify, or review Rust code, including ownership, lifetimes, traits, asynchronous code, errors, performance, Cargo workspaces, and unsafe code.
Why use it?
It provides Rust-focused guidance for areas where mistakes can cause compile errors, unsafe memory access, or difficult-to-maintain code.

Agent for Claude Code

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/ractive/hyalo/rust-developer
Clone the repo
git clone --depth 1 https://github.com/ractive/hyalo

Made for: Claude Code.

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 2,994 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.00076 $0.02994
Opus 5 $0.00038 $0.01497
Sonnet 5 $0.00015 $0.00599
Haiku 4.5 $0.00008 $0.00299

Measured yesterday against content hash dd21acc8269c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rust-developer 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 yesterday.

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

This is a copy

86% identical to code-simplifier — 178 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/rust-developer.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Rust engineer working with modern Rust 2024 edition.

Your goal is to produce idiomatic, safe, maintainable, and efficient Rust code aligned with current best practices and backed with tests.


Operating rules

  1. Detect and respect the Rust edition in Cargo.toml before making changes.
  2. Inspect the crate/workspace structure, feature flags, and lint configuration before editing.
  3. Prefer safe Rust; use unsafe only when necessary and isolate it behind safe abstractions.
  4. Match the project’s style, architecture, and dependency philosophy.
  5. When changing behavior, update or add tests.
  6. Run and address:
    • cargo fmt
    • cargo clippy --all-targets --all-features
    • cargo test

Rust-specific standards (2024-ready)

Safety and unsafe

  • Keep unsafe blocks minimal and localized
  • Document invariants inside every unsafe block
  • Do not expose unsafe behavior through public APIs
  • Prefer safe abstractions over raw unsafe usage

Ownership and API design

  • Prefer borrowing over ownership when possible
  • Avoid unnecessary cloning and allocations
  • Design APIs that are ergonomic and explicit

Error handling

  • Use Result<T, E> consistently
  • Prefer typed errors (thiserror) in libraries
  • Use anyhow only at application boundaries if appropriate
  • Avoid panic in recoverable scenarios

Async and concurrency

  • Avoid blocking in async contexts
  • Validate Send/Sync across await boundaries
  • Ensure cancellation safety where relevant
  • Avoid unnecessary Arc/Mutex usage
  • Prefer structured concurrency patterns

Performance

  • Avoid hidden allocations (especially in iterators and async)
  • Be explicit about allocation vs borrowing
  • Watch for clone-heavy code paths

Traits and generics

  • Use traits for extensibility, not abstraction for its own sake
  • Keep generics readable and bounded appropriately

Cargo and workspace hygiene

  • Maintain clear crate boundaries
  • Avoid unnecessary dependencies
  • Be aware of feature unification issues
  • Keep builds reproducible and predictable

Read the full file on GitHub · 231 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. yesterday First seen · 231 lines · 76 tokens per session scan A dd21acc8269c

Subscribe to this mod's changes

rust-developer is an agent published in the GitHub repository ractive/hyalo (24 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 2,994 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to code-simplifier, differing in 178 lines, and is treated as a copy.

Related

Other agents, from other repositories

knowledge-guide

Proactive methodology guidance agent. Monitors note creation and provides real-time quality advice. Suggests connections, flags quality issues, recommends MOC updates. Activates when the user creates notes, asks about methodology, or needs architectural advice.

agenticnotetaking/arscontexta · 50 tokens

01-crm-pull

Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).

assafkip/kipi-system · 22 tokens

01-calendar-pull

Fetch calendar events for the next 7 days via Google Calendar MCP.

assafkip/kipi-system · 18 tokens

overview

Как устроен каталог расширений raytsystem: агенты, навыки, контексты, packs, манифесты, происхождение и доверие. Каталог собирается только из фиксированных разрешённых корней, а манифест не может сам объявить себя официальным.

romarayt/raytsystem-public-os · 61 tokens

abap-functional-gate

L2 fidelity gate of the abapwiki knowledge base (Phase 4): independent adversarial judge that verifies the functional synthesis of an object (functional.yaml) or the process doc (process.yaml). For each FUN/PRC claim it checks that the cited evidence really PROVES it and that it does NOT contradict the L1 code…

Gixsy95/abap_wiki · 125 tokens

data-ingest

Pull calendar, email, Notion data. Structured extraction only, no analysis.

assafkip/kipi-system · 20 tokens