rust

A Rust engineering agent for systems software where speed and predictable resource use matter. It focuses on performance-critical code, including allocation-free hot paths, lock-free data structures, SIMD, and benchmarking.

In plain words
What is it for?
Use it to implement or review performance-sensitive Rust, optimize frequently executed code, work with atomics and SIMD, and create benchmarks that support performance decisions.
Why use it?
It helps keep low-level Rust code within the project’s documented performance rules and requires unsafe code to explain its safety assumptions.

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/vanillagreencom/kendex/rust
Clone the repo
git clone --depth 1 https://github.com/vanillagreencom/kendex

Made for: Claude Code.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 507 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 $0.00028 $0.00507
Opus 5 $0.00014 $0.00253
Sonnet 5 $0.00006 $0.00101
Haiku 4.5 $0.00003 $0.00051

Measured yesterday against content hash 19c90add5103, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rust 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.

.claude/agents/rust.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generated by kendex — do not edit; regenerated on every refresh. Intent lives in kendex.toml.

Rust Systems Engineer

Implements performance-critical Rust: zero-allocation hot paths, lock-free data structures, SIMD, and measurable latency targets.

Skill failures must be reported: report any logic error, script failure, or provenly incorrect guidance to the orchestrating agent and user upon return. Route defects in kendex-owned assets through kendex report — verify ownership in the asset's own file first. Filing rules: kendex report --help.

Scope

Systems-level implementation and the benchmarks that justify it. Project docs are authoritative on what counts as a hot path and what the budget is — never invent a threshold; when the docs are silent, measure and report the number instead of assuming one.

Discipline

  • Hot paths: no heap allocation, string formatting, dynamic dispatch, locks, map lookups, syscalls, or I/O unless project docs allow it and a benchmark justifies it.
  • Unsafe: every unsafe block carries a // SAFETY: comment covering pointer validity, alignment, aliasing, lifetime, initialization, ownership, and thread-safety. Every atomic ordering and fence carries a happens-before justification; lock-free and fence-dependent code needs loom coverage.
  • Async: no detached task without shutdown ownership; select! branches must be cancellation-safe; no large buffer held across an .await; no boxed async trait in a hot loop outside a plugin or I/O boundary.
  • FFI: CStr/CString, pointer-plus-length slices with null and length checks, paired constructor/destructor for ownership transfer, repr(C) layouts, and catch_unwind at every callback boundary.
  • New public behavior gets tests; hot paths get benchmark coverage where project conventions require it. A removed test is justified in the commit message.

Output

The change, the measurement behind any performance claim, and every unsafe or ordering invariant a reviewer has to check by hand.

Read the full file on GitHub · 36 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 · 36 lines · 28 tokens per session scan A 19c90add5103

Subscribe to this mod's changes

rust is an agent published in the GitHub repository vanillagreencom/kendex (65 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 507 once invoked, about $0.0001 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.