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/reliabilitynpx skills add dean0x/devflow --skill reliabilitygit 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 | $0.00028 | $0.01104 |
| Opus 5 | $0.00014 | $0.00552 |
| Sonnet 5 | $0.00006 | $0.00221 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
reliability scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const res = await fetch(url); How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reliability Patterns
Domain expertise for runtime reliability and defensive bounds analysis. Use alongside devflow:review-methodology for complete reliability reviews.
Iron Law
EVERY OPERATION MUST TERMINATE AND EVERY RESOURCE MUST BE BOUNDED
Adapted from NASA/JPL's "Power of Ten" rules for safety-critical code [1]: every loop must have a fixed upper bound, every resource must have a known lifetime, and every assumption must be checked by an assertion. Unbounded operations are latent outages.
Reliability Categories
1. Bounded Iteration [1]
All loops, retries, and pagination must terminate after a known maximum.
Violation: Unbounded retry loop
while (true) {
const res = await fetch(url);
if (res.ok) break;
await sleep(1000);
}
Solution: Fixed upper bound with explicit failure
const MAX_RETRIES = 5;
for (let attempt = 0; attempt < MAX_RETRIES; attempt++) {
const res = await fetch(url);
if (res.ok) return res;
await sleep(1000 * 2 ** attempt);
}
throw new Error(`Failed after ${MAX_RETRIES} attempts`);
2. Assertion Density [1]
Assert preconditions and invariants in production code, not just tests.
Violation: Silent assumption
function processPayment(order: Order) {
const total = order.items.reduce((sum, i) => sum + i.price, 0);
chargeCard(order.paymentMethod, total);
}
Solution: Explicit precondition checks
function processPayment(order: Order) {
assert(order.items.length > 0, 'Cannot process empty order');
assert(order.paymentMethod != null, 'Missing payment method');
const total = order.items.reduce((sum, i) => sum + i.price, 0);
assert(total > 0, 'Order total must be positive');
chargeCard(order.paymentMethod, total);
}
3. Allocation Discipline [1]
Minimize allocation in hot paths — prefer pre-sized collections, pools, or arenas.
Violation: Allocation in tight loop
func processEvents(events []Event) []Result {
var results []Result
for _, e := range events {
buf := make([]byte, 4096) // alloc per iteration
results = append(results, process(e, buf))
}
return results
}
What ships with it
4 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 · 154 lines · 28 tokens per session scan A 65d275afe2ac
reliability is a skill published in the GitHub repository dean0x/devflow (19 stars, last pushed 2d ago), licensed MIT. It adds 28 tokens to every session and 1,104 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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。.