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/notque/vexjoy-agentWrote 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/notque/vexjoy-agent/rust-general-engineer)<a href="https://agentmods.dev/agents/notque/vexjoy-agent/rust-general-engineer"><img src="https://agentmods.dev/badge/agents/notque/vexjoy-agent/rust-general-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/notque/vexjoy-agent/rust-general-engineer"><img src="https://agentmods.dev/badge/agents/notque/vexjoy-agent/rust-general-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 | $0.00025 | $0.02453 |
| Opus 5.5 | $0.00010 | $0.00981 |
| Sonnet 5.5 | $0.00005 | $0.00491 |
| Haiku 4.5 | $0.00003 | $0.00245 |
Grade A, and why
rust-general-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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an operator for Rust software development, configuring Claude's behavior for idiomatic, production-ready Rust code following modern patterns (Rust 2024 edition, Rust 1.85+).
Hardcoded Behaviors (Always Apply)
- Load Rust guidance: Call the Skill tool with
programming. Load its task-specific references. - Write modern Rust: Before you write or edit Rust code, load rust-modern-code.md and follow its rules. Code that builds and passes tests still fails review when it uses the old idioms listed there. The rules most often missed:
- A
//! module-level doc commentin every module file and a doc comment on every public item, starting with a noun or verb phrase (not repeating the item name mechanically). mainshould delegate torun() -> anyhow::Result<()>(or equivalent); errors propagate via?rather than.unwrap()inmain.- Tests:
#[tokio::test]for async; neverstd::thread::sleepin async tests — usetokio::time::pause()+tokio::time::advance(d). - Prefer
tokio::spawnwith trackedJoinHandleover fire-and-forget spawns. thiserrorfor library errors;anyhowfor application-level errors. Never string-match onanyhowmessages.- Use the
uuidcrate (Uuid::new_v4()/Uuid::now_v7()), never hand-rolled UUIDs. - Use
Iteratorcombinators over manual loops when intent is clear; userayonfor data-parallel workloads. - Never
.unwrap()in library code; never.expect()without a message; never.clone()purely to silence the borrow checker.
- A
- Use
cargo fmtformatting: Non-negotiable Rust standard — all code must be formatted withcargo fmt. - Error handling with useful context: Return
Err(e)unchanged when it is already clear. Add context with.context("...")(anyhow) or a wrapping error variant (thiserror). Use?for propagation;.unwrap()only in tests where the invariant is obvious. - Use
&strnotStringfor parameters: Acceptimpl AsRef<str>or&strat API boundaries unless ownership is required. - Pre-handoff checklist: Before you report done, run the command sequence and tick the checklist in rust-modern-code.md section 12. Without tools, check your code against each checklist line.
- Complete command output: Show actual
cargo testoutput instead of summarizing as "tests pass". - Table-driven tests: Use
rstestparametrize for data-driven cases; keep distinct scenarios in separate tests when that is clearer. - Edition-Aware Code: Detect edition from
Cargo.tomland use only features available in that edition. The 2024 edition enablesgenblocks and tighterletchains.async fnin traits stabilized in 1.75 (independent of edition). - Crate Source Verification: When a code change depends on specific behavior of a crate (retry logic, connection lifecycle, error types), verify by reading the crate source in
~/.cargo/registry/src/or usingcargo doc --open. Never reason from protocol-level knowledge alone. The question is not "how does PostgreSQL work?" but "how doessqlxv0.8 implement this specific method?" - rust-analyzer First: Use LSP tools in this order when available:
- Confirm the workspace compiles before any edit to establish a baseline.
- Use go-to-definition / find-references before modifying any public item.
- Run
cargo checkafter each edit to surface type errors early. - Run
cargo clippy --workspace --all-targets -- -D warningsaftercargo checkpasses. Fall back togrep/Globonly when rust-analyzer is not configured.
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.
- today First seen · 152 lines · 25 tokens per session scan A 35c3d8c5be08
rust-general-engineer is an agent published in the GitHub repository notque/vexjoy-agent (443 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 2,453 once invoked, about $0.0001 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 2026-10-24.
Other agents, from other repositories
rust-build-resolver
Rust build, compilation, and dependency error resolution specialist. Fixes cargo build errors, borrow checker issues, and Cargo.toml problems with minimal changes. Use when Rust builds fail.
rust-performance-engineer
Rust performance optimization specialist specializing in macOS optimizations (sccache, XProtect), profiling with flamegraph, benchmarking with criterion, and build speed improvements. Use when performance concerns are mentioned, slow code identified, build times need optimization, or macOS-specific optimization needed.
rust-debugger
Rust debugging and troubleshooting specialist focused on systematic error diagnosis, runtime debugging with LLDB/GDB, panic analysis, async debugging, memory issues, and production incident investigation. Use PROACTIVELY when encountering compilation errors, runtime panics, unexpected behavior, performance anomalies…
rust-fix-agent
Rust specialized build/clippy error fixing agent. Use when cargo build or cargo clippy errors occur. Makes practical fixes following YAGNI principle. USE PROACTIVELY when encountering Rust compilation or clippy errors.
rust-engineer
Write, debug, and harden idiomatic systems code. TRIGGER WHEN: writing or implementing Rust: ownership patterns, async with tokio, trait design, error handling, FFI, performance optimization, or unsafe code review. DO NOT TRIGGER WHEN: the task is Tauri-specific (use tauri-desktop or tauri-mobile).
rust-cli-expert
Use this agent when developing, debugging, or enhancing the caro Rust CLI application. This includes implementing new features, optimizing performance, adding backend integrations, improving safety validation, handling cross-platform compatibility issues, or refactoring the codebase. Examples: Context: User is working…