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 agentmods add skills/uwuclxdy/agenticat/clean-rustnpx skills add uwuclxdy/agenticat --skill clean-rustgit clone --depth 1 https://github.com/uwuclxdy/agenticatWrote 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/uwuclxdy/agenticat/clean-rust)<a href="https://agentmods.dev/skills/uwuclxdy/agenticat/clean-rust"><img src="https://agentmods.dev/badge/skills/uwuclxdy/agenticat/clean-rust.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.02667 |
| Opus 5 | $0.00015 | $0.01333 |
| Sonnet 5 | $0.00006 | $0.00533 |
| Haiku 4.5 | $0.00003 | $0.00267 |
Grade A, and why
clean-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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Rust
Rust-specific conventions for writing, reviewing, and refactoring. The core rules below always apply. Load the one reference file matching the task's domain; don't load them all.
If the clean-code skill is installed, its language-agnostic principles (function size, naming hygiene, comment discipline) still apply. Where generic advice conflicts with Rust idiom, this skill wins. Classic examples: "prefer exceptions over error codes" maps to Result, never panics; "replace switch with polymorphism" maps to exhaustive match, which in Rust is a feature, not a smell.
| Task touches | File |
|---|---|
| Error types, propagation helpers, failure semantics, retries | references/error-handling.md |
async/await, tokio, select!, channels, spawned child processes |
references/async.md |
| Threads, atomics, lock ordering, drop order | references/concurrency.md |
| Process-global mutable state (env vars, global overrides) across threads | references/edition-2024.md |
| Public API shape, builders, newtypes, typestate, serde | references/api-design.md |
Any unsafe block, FFI, raw pointers, exported symbols |
references/unsafe.md |
| Writing tests or debugging test infrastructure | references/testing.md |
| Hot paths, allocations, string building, hasher choice | references/performance.md |
Benchmarks, criterion, #[bench] |
references/performance.md |
| Secret files on disk, keys and tokens at rest | references/security.md |
| Logging, tracing spans, log levels | references/observability.md |
| Edition 2024 migration or 2024-specific behavior changes | references/edition-2024.md |
Errors
Result+?everywhere; no.unwrap()/.expect()outside tests and one-time init of hand-audited literals (LazyLock<Regex>on a fixed pattern). The rare justifiedexpectcarries a message naming the invariant that makes it safe.- No sentinel returns (
-1,"") for failure.Option<T>for absence that isn't an error. thiserrorfor library errors (callers can match),anyhow/eyreat the application boundary. NeverBox<dyn Error>orStringas a library error type.- Bind a
Resultonce withmatch/if let/let-else, never.is_ok()followed by separate access or a downstream.unwrap(). - Pick one failure semantics per operation: best-effort (warn per item,
Ok(())at end) or fail-fast (propagate first error). Never warn-per-item and then fail at the end; that surprises exit-code consumers.
What ships with it
10 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.
- references/api-design.md 4.7 KB
- references/async.md 4.3 KB
- references/concurrency.md 3.9 KB
- references/edition-2024.md 3.0 KB
- references/error-handling.md 3.9 KB
- references/observability.md 2.2 KB
- references/performance.md 4.3 KB
- references/security.md 2.0 KB
- references/testing.md 4.6 KB
- references/unsafe.md 2.9 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.
- 6d ago First seen · 141 lines · 29 tokens per session scan A 9890fba05688
clean-rust is a skill published in the GitHub repository uwuclxdy/agenticat (5 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 2,667 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 2026-08-31.
Other skills, from other repositories
azure-storage-blob-rust
Azure Blob Storage library for Rust. Upload, download, and manage blobs and containers. Triggers: "blob storage rust", "BlobClient rust", "upload blob rust", "download blob rust", "storage container rust", "BlobServiceClient rust".
azure-keyvault-certificates-rust
Azure Key Vault Certificates library for Rust. Create, manage, and use X.509 certificates including self-signed and CA-issued. Triggers: "keyvault certificates rust", "CertificateClient rust", "create certificate rust", "self-signed certificate rust", "X.509 rust".
azure-cosmos-rust
Azure Cosmos DB library for Rust (NoSQL API). Document CRUD, containers, and globally distributed data. Triggers: "cosmos db rust", "CosmosClient rust", "document crud rust", "NoSQL rust", "partition key rust".
azure-eventhub-rust
Azure Event Hubs library for Rust. Send and receive events for streaming data ingestion and batch processing. Triggers: "event hubs rust", "ProducerClient rust", "ConsumerClient rust", "send event rust", "streaming rust", "eventhub rust".
azure-identity-rust
Azure Identity library for Rust. Microsoft Entra ID authentication for all Azure SDK clients. Triggers: "azure identity rust", "DeveloperToolsCredential", "authentication rust", "managed identity rust", "credential rust", "Entra ID rust".
azure-keyvault-keys-rust
Azure Key Vault Keys library for Rust. Create, manage, and use cryptographic keys including RSA, EC, and HSM-protected keys. Triggers: "keyvault keys rust", "KeyClient rust", "create key rust", "encrypt rust", "wrap key rust", "sign rust".