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/condevtools/pr-agent/frontend-fullchain-optimizationnpx skills add condevtools/pr-agent --skill frontend-fullchain-optimizationgit clone --depth 1 https://github.com/condevtools/pr-agentWhat 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 | $0.00080 | $0.08450 |
| Opus 5 | $0.00040 | $0.04225 |
| Sonnet 5 | $0.00016 | $0.01690 |
| Haiku 4.5 | $0.00008 | $0.00845 |
Grade A, and why
frontend-fullchain-optimization 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.
curl -X POST "https://your-cdn-provider.example.com/purge" \ How it starts
The opening of the file, as written. The whole thing — 566 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Full-Chain Performance Optimization Guide / 前端全链路性能优化指南
A frontend performance diagnostic and optimization system based on Web Vitals core metrics. Core principle: User-centric — optimization is about doing less, not more.
基于 Web Vitals 核心指标的前端性能诊断与优化体系。核心原则：以用户为中心，优化就是做减法。
Metric Threshold Quick Reference / 指标阈值速查
| Metric / 指标 | Good | Needs Improvement | Poor | Unit / 单位 | Focus / 关注点 |
|---|---|---|---|---|---|
| LCP | ≤ 2.5s | 2.5s - 4s | > 4s | Time / 时间 | Largest Contentful Paint / 最大内容渲染 |
| FCP | ≤ 1.8s | 1.8s - 3s | > 3s | Time / 时间 | First Contentful Paint / 首次内容绘制 |
| INP | ≤ 200ms | 200ms - 500ms | > 500ms | Time / 时间 | Interaction to Next Paint / 交互响应延迟 |
| CLS | ≤ 0.1 | 0.1 - 0.25 | > 0.25 | Score / 分数 | Visual Stability / 视觉稳定性 |
| TTFB | ≤ 800ms | 800ms - 1.8s | > 1.8s | Time / 时间 | Time to First Byte / 首字节时间 |
| FID | ≤ 100ms | 100ms - 300ms | > 300ms | Time / 时间 | First Input Delay / 首次输入延迟 |
| TBT | Tasks > 50ms are long tasks | — | — | Time / 时间 | Total Blocking Time / 总阻塞时间 |
Measurement advice: Don't rely on a single P75. Combine P60/P75/P90/P99 percentiles with daily avg/max/min trend lines. Desktop: target P98+; Mobile core pages: target P95–P99.
衡量建议：不使用单一 P75，应综合 P60/P75/P90/P99 四个百分位 + 日均/最大/最小值折线图判断。PC 端建议 P98+，移动端核心页面建议 P95-P99。
Diagnostic Decision Tree / 诊断决策树
Page loads slowly? / 页面加载慢？
├── TTFB > 800ms → Network/server issue → See "TTFB Optimization"
│ → 网络/服务器问题 → 见「TTFB 优化」
├── FCP > 1.8s → Resource blocking/large files → See "FCP Optimization"
│ → 资源阻塞/文件过大 → 见「FCP 优化」
├── LCP > 2.5s
│ ├── TTFB & FCP normal → Slow viewport resource loading → See "LCP Optimization"
│ │ → 视口资源加载慢 → 见「LCP 优化」
│ └── TTFB or FCP abnormal → Fix upstream metrics first
│ → 先解决上游指标
├── INP > 200ms → Long tasks blocking main thread → See "INP Optimization"
│ → 长任务阻塞主线程 → 见「INP 优化」
├── CLS > 0.1 → Layout shifts → See "CLS Optimization"
│ → 布局偏移 → 见「CLS 优化」
└── Lighthouse Performance Score / Lighthouse 性能分数
├── > 80: Few issues / 问题较少
├── 60-80: Needs focused analysis, priority: FCP → LCP → CLS
│ 需重点分析，优先级 FCP → LCP → CLS
└── < 60: Severe issues, full audit required
严重问题，全面排查
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 · 566 lines · 80 tokens per session scan A 0847bef27821
frontend-fullchain-optimization is a skill published in the GitHub repository condevtools/pr-agent (37 stars, last pushed 5mo ago), licensed MIT. It adds 80 tokens to every session and 8,450 once invoked, about $0.0004 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
issue-comment
Handle a non-build maintainer comment on an issue or PR — close, reopen, label, dedupe, answer a brief question, or triage. Action-only; redirect anything that needs code changes to /build.
github
Create issues, PRs, clone repos, and manage git workflows.
issue-triage
Triage GitHub issues through the canonical state machine — classify, label, deduplicate, request missing info, write agent briefs, and manage stale issues. Use on demand or on a triage cron.
issue-answer
Answer a question directly — a sourced, neutral reply to an information/explanation/comparison request, from a GitHub issue or a Slack thread. Research repo docs and the web, output the answer, label question (GitHub only), leave open. Never write an agent brief, mark ready-for-agent, or change code.
pr-comment
Answer a maintainer's question about an open PR with concrete, code-cited evidence. The PR-side counterpart to issue-comment — for questions tied to the diff, not a full review.
linear
Linear project management — issues, cycles, and projects via GraphQL API.