rtk is a command-line proxy that filters and compresses output from development commands before it reaches an LLM's context. It is used with coding agents to reduce the tokens consumed by commands such as Git operations. The catalogue includes skills, commands, agents, and instructions for using rtk in agent workflows.
Borrowing it
Nothing to install: this file belongs to rtk-ai/rtk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rtk-ai/rtk/develop/.claude/skills/design-patterns/SKILL.mdgit clone --depth 1 https://github.com/rtk-ai/rtkWrote 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/rtk-ai/rtk/design-patterns)<a href="https://agentmods.dev/skills/rtk-ai/rtk/design-patterns"><img src="https://agentmods.dev/badge/skills/rtk-ai/rtk/design-patterns/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/rtk-ai/rtk/design-patterns"><img src="https://agentmods.dev/badge/skills/rtk-ai/rtk/design-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high YARA Match · line 165 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00042 | $0.01812 |
| Opus 5.5 | $0.00017 | $0.00725 |
| Sonnet 5.5 | $0.00008 | $0.00362 |
| Haiku 4.5 | $0.00004 | $0.00181 |
Grade A, and why
design-patterns 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RTK Rust Design Patterns
Patterns that apply to RTK's filter module architecture. Focused on CLI tool patterns, not web/service patterns.
Pattern 1: Newtype (Type Safety)
Use when: wrapping primitive types to prevent misuse (command names, paths, token counts).
// Without Newtype — easy to mix up
fn track(input_tokens: usize, output_tokens: usize) { ... }
track(output_tokens, input_tokens); // Silent bug!
// With Newtype — compile error on swap
pub struct InputTokens(pub usize);
pub struct OutputTokens(pub usize);
fn track(input: InputTokens, output: OutputTokens) { ... }
track(OutputTokens(100), InputTokens(400)); // Compile error ✅
// Practical RTK example: command name validation
pub struct CommandName(String);
impl CommandName {
pub fn new(s: &str) -> Result<Self> {
if s.contains(';') || s.contains('|') || s.contains('`') {
anyhow::bail!("Invalid command name: shell metacharacters");
}
Ok(Self(s.to_string()))
}
pub fn as_str(&self) -> &str { &self.0 }
}
Pattern 2: Builder (Complex Configuration)
Use when: a struct has 4+ optional fields, many with defaults.
#[derive(Default)]
pub struct FilterConfig {
max_lines: Option<usize>,
strip_ansi: bool,
show_warnings: bool,
truncate_at: Option<usize>,
}
impl FilterConfig {
pub fn new() -> Self { Self::default() }
pub fn max_lines(mut self, n: usize) -> Self { self.max_lines = Some(n); self }
pub fn strip_ansi(mut self, v: bool) -> Self { self.strip_ansi = v; self }
pub fn show_warnings(mut self, v: bool) -> Self { self.show_warnings = v; self }
}
// Usage — readable, no positional arg confusion
let config = FilterConfig::new()
.max_lines(50)
.strip_ansi(true)
.show_warnings(false);
When NOT to use Builder: if the struct has 1-3 fields with obvious meaning. Over-engineering for simple cases.
Pattern 3: State Machine (Parser/Filter Flows)
Use when: parsing multi-section output (test results, build output) where context changes behavior.
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 · 249 lines · 42 tokens per session scan A 5618acc51803
design-patterns is a skill published in the GitHub repository rtk-ai/rtk (84,655 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 1,812 once invoked, about $0.0002 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
design-patterns
Rust design patterns for RTK. Newtype, Builder, RAII, Trait Objects, State Machine. Applied to CLI filter modules. Use when designing new modules or refactoring existing ones.
Codex-skill-rust
Guide for Rust development including code style, testing, building, and quality checks using cargo tools. Apply when working with Rust code, Cargo.toml, or running cargo commands.
rust-crate-ci
Load before editing any Rust crate in this repo (currently runners/swarm-sandbox-runner). Covers the mandatory local validation gate, common rustfmt/clippy pitfalls, and Windows-specific Rust correctness patterns that CI enforces but are hard to catch locally without a Windows toolchain.
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…
rust
Expert in Rust development with focus on safety, performance, and async programming.
plugin-system
Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).