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/ractive/hyalo/review-rustnpx skills add ractive/hyalo --skill review-rustgit clone --depth 1 https://github.com/ractive/hyaloWrote 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/ractive/hyalo/review-rust)<a href="https://agentmods.dev/skills/ractive/hyalo/review-rust"><img src="https://agentmods.dev/badge/skills/ractive/hyalo/review-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 | $0.00177 | $0.03755 |
| Opus 5 | $0.00088 | $0.01878 |
| Sonnet 5 | $0.00035 | $0.00751 |
| Haiku 4.5 | $0.00018 | $0.00376 |
Grade A, and why
review-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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust Code Review (Edition 2024)
You are performing a critical code review of Rust code targeting edition 2024. Your job is to find real problems — not to rubber-stamp or nitpick formatting. Focus on correctness, safety, idiomatic patterns, and maintainability in that order.
Determine Review Scope
First, figure out what you're reviewing:
- PR review: Use
git diffagainst the base branch to identify changed files. Focus review on the diff, but read surrounding context to understand impact. - Crate/module review: Read the specified crate or module top-down. Start with
lib.rsormod.rsto understand the public API surface, then drill into implementation. - Full codebase review: Start with
Cargo.toml(workspace layout, edition, dependencies), then review each crate systematically. Prioritize public API surfaces and core logic.
For PR reviews, also check:
- Does the PR title/description match what the code actually does?
- Are there unrelated changes mixed in?
- Is the diff a reasonable size, or should it be split?
Review Process
Work through these categories in order. Not every category applies to every review — skip sections that aren't relevant to the code at hand. Spend your time proportional to risk.
1. Correctness
This is the most important category. Bugs ship when reviewers focus on style instead of logic.
- Logic errors: Trace the happy path and key error paths mentally. Look for off-by-one, wrong comparison operators, swapped arguments, incorrect boolean logic.
- Edge cases: What happens with empty collections, zero values,
None, maximum values, concurrent access? Does the code handle them or silently produce wrong results? - Error handling: Are errors propagated correctly? Watch for
unwrap()andexpect()on values that can legitimately fail at runtime. Using?is good — but is the error type meaningful to the caller, or does it erase important context? - Resource management: Are files, connections, locks released properly? Rust's RAII helps,
but watch for
std::mem::forget, leakedBox::into_raw, or holding locks across.await. - Integer overflow: Debug builds panic, release builds wrap. If the code does arithmetic on
user-provided values, are
checked_*orsaturating_*methods used?
What ships with it
1 file 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.
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 · 281 lines · 177 tokens per session scan A 6c765344eb7c
review-rust is a skill published in the GitHub repository ractive/hyalo (24 stars, last pushed yesterday), licensed MIT. It adds 177 tokens to every session and 3,755 once invoked, about $0.0009 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.
Other skills, from other repositories
migrate-v0-to-v1
Migrate a Scraps wiki from v0 to v1. Use this whenever the user asks to upgrade Scraps, migrate v0 wiki syntax/config, convert implicit tags to explicit #[[tag]], move from scraps-writer to scraps, or audit a wiki for v1 readiness. This skill is designed for one-pass LLM-led migrations that discover the latest v0 and…
reduce
Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract…
rethink
Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".
ingest
Create a new scrap from a source (prompt, URL, or arbitrary markdown), update cross-links in related scraps, and run a sanity check. Use this when the user wants to add a scrap, summarize an article, save synthesized content to the wiki, or file back a Q&A result.
dioxus-knowledge-patch
Use this skill when creating, migrating, debugging, testing, or packaging a Dioxus application. Inspect manifests and the target platform, then open the matching topic reference.
graph
Interactive knowledge graph analysis. Routes natural language questions to graph scripts, interprets results in domain vocabulary, and suggests concrete actions. Triggers on "/graph", "/graph health", "/graph triangles", "find synthesis opportunities", "graph analysis".