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/changan-su/forsion/frontend-code-reviewnpx skills add Changan-Su/Forsion --skill frontend-code-reviewgit clone --depth 1 https://github.com/Changan-Su/ForsionWrote 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/changan-su/forsion/frontend-code-review)<a href="https://agentmods.dev/skills/changan-su/forsion/frontend-code-review"><img src="https://agentmods.dev/badge/skills/changan-su/forsion/frontend-code-review.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00175 | $0.01929 |
| Opus 5 | $0.00088 | $0.00964 |
| Sonnet 5 | $0.00035 | $0.00386 |
| Haiku 4.5 | $0.00017 | $0.00193 |
Grade A, and why
前端代码审查 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 5d 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.
fetch(url, { signal: ac.signal }); The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 5d ago First seen · 105 lines · 175 tokens per session scan A 99dd9545feaf
前端代码审查 is a skill published in the GitHub repository Changan-Su/Forsion (114 stars, last pushed 5d ago), with no licence file. It adds 175 tokens to every session and 1,929 once invoked, about $0.0009 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
add-tauri-command
Use when adding a new Tauri command to Cowork-Z — a new backend capability the React frontend must call, a new #[tauri::command] fn, or a new invoke() wrapper in tauri-api.ts. Also use when a newly written command returns "Command not found" at runtime.
nextjs-code-review
为 Next.js 应用提供全面代码评审，校验 Server Components、Client Components、Server Actions、缓存策略、metadata、API 路由、中间件与性能模式。在评审 Next.js App Router 代码改动、合并 PR 前、实现新功能后或做架构校验时使用。.
infographic
生成精美的纯 HTML+CSS 信息图 — 时间线、流程、对比分析、SWOT、金字塔、漏斗、数据卡片、组织架构等。无需外部依赖，在沙箱 iframe 中渲染。适合将结构化信息以海报级视觉效果呈现。.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
init
Skill "init" from PM-Shawn/Abu-Cowork, covering 前置检查, 初始化流程, 第一步：分析项目结构, 第二步：生成 abu.md and 项目规则.
reflect
Skill "reflect" from PM-Shawn/Abu-Cowork, covering 复盘助手, 复盘框架, 1. 任务回顾, 2. 经验教训 and 3. 可沉淀的模式.