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/performancenpx skills add dean0x/devflow --skill performancegit 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 | $0.00026 | $0.01276 |
| Opus 5 | $0.00013 | $0.00638 |
| Sonnet 5 | $0.00005 | $0.00255 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
performance 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Patterns
Domain expertise for performance optimization and bottleneck detection. Use alongside devflow:review-methodology for complete performance reviews.
Iron Law
MEASURE BEFORE OPTIMIZING
Profile first, optimize second. Every performance claim requires benchmarks. Brendan Gregg's USE Method [1] (Utilization, Saturation, Errors) and Tom Wilkie's RED Method [2] (Rate, Errors, Duration) are the systematic starting points — not guesswork. Gil Tene's coordinated omission warning [8]: averages lie — monitor P99, not mean latency.
Measurement Foundation [1][2][7][8][9]
| Method | For | Measures |
|---|---|---|
| USE Method [1] | System resources | Utilization, Saturation, Errors per resource |
| RED Method [2] | Services | Rate, Errors, Duration per endpoint |
| Flame Graphs [9] | CPU hot paths | Widest frames = hottest code — optimize those |
| HDR Histogram [8] | Latency | Full distribution without coordinated omission |
Latency hierarchy [7]: L1 cache ~1ns · L2 ~4ns · L3 ~40ns · RAM ~100ns · SSD ~100µs · Network (DC) ~500µs · HDD ~10ms. Knowing these prevents optimizing the wrong layer [4].
Performance Categories
1. Algorithmic Issues [5][12]
N+1 Query Problem — database query inside a loop. O(n) round-trips [5].
// VIOLATION: 1 + N queries — O(n) round-trips [5]
for (const user of users) {
user.orders = await db.orders.findByUserId(user.id);
}
// CORRECT: Batch query with Map lookup — O(1) per access [5]
const orders = await db.orders.findAll({ where: { userId: userIds } });
const ordersByUser = new Map(groupBy(orders, 'userId'));
users.forEach(u => u.orders = ordersByUser.get(u.id) || []);
O(n²) Patterns — linear search inside a loop [12].
// VIOLATION: Array.includes is O(n), called n times → O(n²) [12]
items.filter(item => selected.includes(item.id));
// CORRECT: Set lookup is O(1) → total O(n) [12]
const selectedSet = new Set(selected);
items.filter(item => selectedSet.has(item.id));
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 · 136 lines · 26 tokens per session scan A 426f9c5c96c7
performance is a skill published in the GitHub repository dean0x/devflow (19 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 1,276 once invoked, about $0.0001 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。.