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/dean0x/devflow/rustnpx skills add dean0x/devflow --skill rustgit clone --depth 1 https://github.com/dean0x/devflowWhat 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 | $0.00063 | $0.01360 |
| Opus 5 | $0.00032 | $0.00680 |
| Sonnet 5 | $0.00013 | $0.00272 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
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 2d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust Patterns
Reference for Rust-specific patterns, ownership model, and type-driven design.
Iron Law
MAKE ILLEGAL STATES UNREPRESENTABLE [15][2, C-VALIDATE]
Encode invariants in the type system. If a function can fail, return
Result. If a value might be absent, returnOption. If a state transition is invalid, make it uncompilable. Runtime checks are a fallback, not a strategy.
When This Skill Activates
- Working with Rust codebases
- Designing type-safe APIs
- Managing ownership and borrowing
- Implementing error handling
- Writing concurrent code
Ownership & Borrowing [1, Ch.4][11]
Prefer borrowing over cloning — accept &str not String, &[T] not &Vec<T> [2, C-BORROW].
The borrow checker enforces the Stacked Borrows aliasing model at compile time [6][11].
Lifetime annotations required when elision rules can't resolve ambiguity [1, Ch.10].
// BAD: fn process(data: String) — takes ownership unnecessarily
fn process(data: &str) -> usize { data.len() } // GOOD: borrow [2, C-BORROW]
See references/ownership.md for elision rules, interior mutability, Cow, and Pin.
Error Handling [8][9][16]
Use thiserror for libraries (typed, matchable variants); anyhow for applications
(ergonomic propagation). Never use Box<dyn Error> in library APIs [8][16].
#[derive(thiserror::Error, Debug)]
pub enum AppError {
#[error("IO error reading {path}")]
Io { path: String, #[source] source: io::Error },
#[error("{entity} with id {id} not found")]
NotFound { entity: String, id: String },
}
// ? operator propagates with source context [1, Ch.9]
fn read_config(path: &str) -> Result<Config, AppError> {
let raw = fs::read_to_string(path).map_err(|e| AppError::Io { path: path.into(), source: e })?;
toml::from_str(&raw).map_err(|e| AppError::Parse { source: e })
}
Type System
Newtype Pattern [2, C-NEWTYPE][15]
struct UserId(String); struct OrderId(String);
// Can't accidentally swap — compiler enforces [15]
fn get_order(user_id: &UserId, order_id: &OrderId) -> Result<Order, AppError> { todo!() }
What ships with it
5 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.
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.
- 2d ago First seen · 149 lines · 63 tokens per session scan A d0aa3dabd143
rust is a skill published in the GitHub repository dean0x/devflow (19 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 1,360 once invoked, about $0.0003 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
data-engineering
Skill "data-engineering" from fengshao1227/ccg-workflow, covering 数据工程域 · data engineering, 域概览, 数据管道编排, 框架对比 and airflow 核心模式.
verify-change
变更校验关卡。分析代码变更,检测文档同步状态,评估变更影响范围。当用户提到变更检查、文档同步、代码审查、提交前检查、diff分析时使用。在设计级变更、重构完成时自动触发。.
verify-security
安全校验关卡。自动扫描代码安全漏洞,检测危险模式,确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
gen-docs
文档生成器。自动分析模块结构,生成 README.md 和 DESIGN.md 骨架。当用户提到生成文档、创建README、创建DESIGN、文档骨架、文档模板时使用。在新建模块开始时自动触发。.
verify-module
模块完整性校验关卡。扫描目录结构、检测缺失文档、验证代码与文档同步。当用户提到模块校验、文档检查、结构完整性、README检查、DESIGN检查时使用。在新建模块完成时自动触发。.