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/phuonghx/aim-cli/rust-pronpx skills add phuonghx/aim-cli --skill rust-progit clone --depth 1 https://github.com/phuonghx/aim-cliWhat 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 | $0.00095 | $0.01638 |
| Opus 5 | $0.00048 | $0.00819 |
| Sonnet 5 | $0.00019 | $0.00328 |
| Haiku 4.5 | $0.00010 | $0.00164 |
Grade A, and why
rust-pro 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.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modern Rust
Guidance for building correct, fast Rust on the 2024 edition. The throughline is using the compiler to prove properties at build time, then optimizing what is left -- safety and performance are not in tension when the type system carries the weight.
How to approach a Rust task
- Pin down the real constraints first: latency and throughput targets, safety requirements, and which runtime (if any) the system can adopt.
- Decide the concurrency model and the crate ecosystem before writing much code -- async runtime, web framework, data layer.
- Build with tests and lints wired in from the start.
- Profile only after it works, then optimize the hot paths the data points to.
This skill suits services, libraries, and systems tooling, and is most valuable for ownership/lifetime puzzles, async architecture, and safety-preserving optimization. It is overkill when you just need a quick dynamic script or only touch basic syntax, and it does not apply where Rust cannot enter the stack.
Language features worth mastering
The modern, long-stable surface area is large. The pieces that pay off most often:
- Const generics and improved inference for expressing size and shape at the type level.
- Generic associated types (GATs) and richer trait bounds for abstractions that were previously impossible.
- Pattern matching with destructuring and guards as a primary control-flow tool.
- Const evaluation for moving work to compile time.
- Both flavors of macro -- declarative
macro_rules!and procedural/derive -- for cutting boilerplate. - The module and visibility system for clean API surfaces.
Result,Option, and custom error types as the backbone of error handling.
Ownership and memory
This is where Rust earns its guarantees, so internalize it:
- Ownership, borrowing, and move semantics -- the model the borrow checker enforces.
- Shared ownership via
Rc/Arc, withWeakto break cycles. - The smart-pointer toolbox:
Boxfor heap allocation,RefCellfor interior mutability,Mutex/RwLockfor shared mutable state across threads. - Zero-cost abstractions and deliberate memory layout.
- RAII -- tie resource cleanup to scope via
Drop. - Phantom types and zero-sized types to encode invariants at no runtime cost.
- Custom allocators and pooling when the default allocator is the bottleneck.
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 First seen · 142 lines · 95 tokens per session scan A 5efaad16b2e0
rust-pro is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 1,638 once invoked, about $0.0005 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
hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
user-persona
Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).