Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Nevaberry/nevaberry-pluginsnpx agentmods add skills/nevaberry/nevaberry-plugins/cargo-knowledge-patchWrote 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/nevaberry/nevaberry-plugins/cargo-knowledge-patch)<a href="https://agentmods.dev/skills/nevaberry/nevaberry-plugins/cargo-knowledge-patch"><img src="https://agentmods.dev/badge/skills/nevaberry/nevaberry-plugins/cargo-knowledge-patch/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/nevaberry/nevaberry-plugins/cargo-knowledge-patch"><img src="https://agentmods.dev/badge/skills/nevaberry/nevaberry-plugins/cargo-knowledge-patch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 77 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00007 | $0.01816 |
| Opus 5.5 | $0.00003 | $0.00726 |
| Sonnet 5.5 | $0.00001 | $0.00363 |
| Haiku 4.5 | $0.00001 | $0.00182 |
Grade A, and why
cargo-knowledge-patch 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 1mo 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cargo Knowledge Patch
Use this skill when changing Cargo manifests, configuration, dependency workflows, builds, workspaces, packaging, publishing, Cargo scripts, or unstable Cargo features. Inspect the repository and installed toolchain before applying the guidance: project manifests, lockfiles, configuration, tests, and observed behavior take precedence.
Working method
- Run
cargo --versionand identify whether the repository pins a toolchain. - Inspect
Cargo.toml,Cargo.lock,.cargo/config.toml, workspace manifests, and CI commands relevant to the task. - Separate stable behavior from features that still require nightly Cargo
and
-Zflags. - Check the compatibility and removal notes before copying an older command line or configuration key.
- Open the task-specific reference from the index and preserve the repository's minimum supported Rust version.
- Validate manifest and configuration changes with the narrowest applicable Cargo command before running the full project test suite.
Reference index
| Reference | Topics |
|---|---|
| upgrades-and-compatibility.md | Security fixes, removals, deprecations, changed defaults, platform requirements, migration hazards |
| configuration-networking-and-cache.md | Configuration merging and includes, cache cleanup, Git and SSH, proxies, runners, warning policy |
| builds-targets-and-artifacts.md | Editions, targets, build directories, rustc and rustdoc, profiles, doctests, artifacts, cleaning |
| workspaces-dependencies-and-metadata.md | Workspaces, feature unification, dependency trees, metadata, vendoring, target filtering |
| packaging-publishing-and-registries.md | Package validation, archives, workspace publishing, registry data and APIs |
| scripts-build-scripts-and-subcommands.md | Cargo scripts, build-script environment and metadata, external subcommands, completions and help |
| unstable-analysis-and-lints.md | Build analysis, timings, SBOM data, Cargo lints, unit graphs, experimental build controls |
What ships with it
8 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.
- coverage.json 1.5 KB
- references/builds-targets-and-artifacts.md 5.9 KB
- references/configuration-networking-and-cache.md 4.7 KB
- references/packaging-publishing-and-registries.md 3.9 KB
- references/scripts-build-scripts-and-subcommands.md 3.7 KB
- references/unstable-analysis-and-lints.md 4.7 KB
- references/upgrades-and-compatibility.md 5.9 KB
- references/workspaces-dependencies-and-metadata.md 3.7 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.
- 1mo ago First seen · 219 lines · 7 tokens per session scan A de0f99747d9d
cargo-knowledge-patch is a skill published in the GitHub repository Nevaberry/nevaberry-plugins (23 stars, last pushed 1mo ago), licensed MIT. It adds 7 tokens to every session and 1,816 once invoked, about $0.0000 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-network-module
Add Rust async networking modules with project-adapted listener lifecycle, protocol parsing, and meaningful tests. Includes Tokio TCP and example wire-protocol templates for nat464-sidecar or compatible Rust projects.
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
rust-systems
Build and upgrade Rust services, CLI and systems components with explicit error, async and resource contracts. Use when working on Rust ownership, concurrency, serialization or unsafe boundaries; preserve MSRV and edition compatibility unless their migration is requested.
agent-rust-expert
Specialist subagent: Rust ownership/borrowing, async Rust, Axum/Actix web frameworks, and WASM specialist. Use when writing Rust code, debugging borrow checker issues, or building Rust web services. Trigger phrases: Rust, borrow checker, ownership, lifetime, Axum, Actix, tokio, async Rust, WASM, wasm-bindgen, cargo…
cloudflare-workers-multi-lang
Multi-language Workers development with Rust, Python, and WebAssembly. Use when building Workers in languages other than JavaScript/TypeScript, or when integrating WASM modules for performance-critical code.
wasm
WebAssembly (WASM) integration, WASI, component model, Rust/Go to WASM compilation. Use when implementing WASM modules, browser/edge compute, or polyglot runtime.