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.
npx skills add martinholovsky/SOTA-skills --skill sota-rustgit clone --depth 1 https://github.com/martinholovsky/SOTA-skillsWrote 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/skills/martinholovsky/sota-skills/sota-rust)<a href="https://agentmods.dev/skills/martinholovsky/sota-skills/sota-rust"><img src="https://agentmods.dev/badge/skills/martinholovsky/sota-skills/sota-rust/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/skills/martinholovsky/sota-skills/sota-rust"><img src="https://agentmods.dev/badge/skills/martinholovsky/sota-skills/sota-rust.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 | $0.00228 | $0.03902 |
| Opus 5.5 | $0.00091 | $0.01561 |
| Sonnet 5.5 | $0.00046 | $0.00780 |
| Haiku 4.5 | $0.00023 | $0.00390 |
Grade A, and why
sota-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.
The source is not reproduced here
Licensed CC-BY-4.0
The repository is licensed CC-BY-4.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- rules/01-ownership-and-api-design.md 21 KB
- rules/02-errors-and-panics.md 18 KB
- rules/03-unsafe-discipline.md 23 KB
- rules/04-async-tokio.md 17 KB
- rules/05-security-supply-chain.md 35 KB
- rules/06-performance.md 14 KB
- rules/07-tooling-ci.md 32 KB
- rules/08-external-programs.md 11 KB
- rules/09-formal-verification.md 25 KB
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.
- yesterday Changed · +4 lines · +29 tokens per session fbd8e59bedeb
- 2d ago Changed · +3 lines f0fe11063d38
- 5d ago Changed · +8 lines b731d73fe2ca
- 7d ago Changed · +1 lines 76b5cd9e01c9
- 17d ago Changed 9f7a49ad1e2f
- 1mo ago Changed 55d1ecdb8665
- 1mo ago Changed · +1 lines 0e09aec630fc
- 1mo ago Changed 7202473f0245
- 2mo ago First seen · 153 lines · 199 tokens per session scan A 86d9b9b08443
sota-rust is a skill published in the GitHub repository martinholovsky/SOTA-skills (24 stars, last pushed yesterday), licensed CC-BY-4.0. It adds 228 tokens to every session and 3,902 once invoked, about $0.0009 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 skills, from other repositories
rust-conventions
Use when a ticket adds or changes Rust code and it must follow the repo's Rust conventions — ownership and borrowing done right, explicit error handling with Result and typed errors, no needless unsafe or clones, idiomatic traits and iterators per the Rust API Guidelines, async/tokio used without blocking or…
cargo-workflows
Manage Rust projects effectively with Cargo workspaces, features, and tooling. Use when the user sets up Cargo workspaces, configures feature flags, writes build.rs scripts, prepares crates for publishing, or uses cargo clippy, cargo fmt, and other Cargo development tools.
error-handling-rust
Implement idiomatic Rust error handling with Result, Option, and the ? operator. Use when the user handles errors in Rust, creates custom error types, uses thiserror or anyhow, implements the From trait for error conversion, or asks about Result/Option patterns and error composition strategies.
ownership-borrowing
Master Rust's ownership, borrowing, and lifetime system for memory-safe code. Use when the user encounters borrow checker errors, lifetime annotations, needs smart pointers (Box/Rc/Arc), works with move semantics, or asks about Clone vs Copy, ownership transfer, and reference management in Rust.
yoagent
Use when building, extending or upgrading an agent on the yoagent Rust crate. Maps each job (tools, policies, verifiers, budgets, sub-agents, plugins from other ecosystems, retries, structured output, tests) to the yoagent feature for it, with tips, pitfalls and what changed per version.
rust-string-enums
Define or refactor Rust string-valued enums and their Serde adapters in litellm-rust, using Strum and serdewith while preserving parsing, wire values, and schemas.