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/design-reviewnpx skills add dean0x/devflow --skill design-reviewgit 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 | $0.00045 | $0.01414 |
| Opus 5 | $0.00023 | $0.00707 |
| Sonnet 5 | $0.00009 | $0.00283 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
design-review 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Review
Anti-pattern detection for implementation plans. Catches structural problems before they become code.
Iron Law
CATCH IT IN THE PLAN, NOT IN THE PR
A plan that implies N+1 queries will produce N+1 queries. A plan that omits error handling will produce code with no error handling. Review the plan as rigorously as you review the code — the plan is the blueprint that every implementation decision follows.
Anti-Pattern Detection Rules
1. N+1 Queries
What to look for in a plan:
- Steps that fetch a list, then loop to fetch related data per item
- "For each X, get Y" language without mentioning batch operations
- JOIN or batch-fetch never mentioned for related data
- "Display X with Y" without specifying how Y is fetched
How to flag:
[N+1 RISK] Step {N}: "{quoted plan text}" — fetches {entity} per iteration.
Resolution: Replace loop with batch query: {proposed batch operation}.
What to suggest instead:
- Identify all IDs in the list first, then batch-fetch related records in one query
- Use ORM eager loading (
.include,.with, JOIN) at the list query level - Cache frequently accessed related data at the service layer
2. God Functions
What to look for in a plan:
- Single step handling more than 3 distinct responsibilities
- "Validate AND process AND notify AND log AND update" in one step
- Steps described as "the main handler" that touch multiple subsystems
- No clear single-sentence description of what the function does
How to flag:
[GOD FUNCTION RISK] Step {N}: "{quoted plan text}" — handles {n} responsibilities.
Resolution: Split into: {responsibility 1} → {responsibility 2} → {responsibility 3}.
What to suggest instead:
- Each function should have a single, clear sentence description of its purpose
- Extract notification, logging, and side effects to separate functions
- Orchestrate composition at a higher level (service layer calls multiple focused functions)
3. Missing Parallelism
What ships with it
1 file 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 · 156 lines · 45 tokens per session scan A c594e416f95d
design-review is a skill published in the GitHub repository dean0x/devflow (19 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 1,414 once invoked, about $0.0002 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
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.
ccg-skills
CCG Skills - Quality gates, documentation generator, and multi-agent orchestration. Auto-installed by CCG workflow system.
architecture
架构设计能力索引。API设计、安全架构、云原生、数据安全。当用户提到架构、设计、API、云原生时路由到此。.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.