What is frontend-fullchain-optimization?

A guide to finding and fixing slow or unstable web pages using Web Vitals, measurements that describe loading speed, interaction response and visual stability. It covers metrics such as LCP, FCP, INP, CLS, TTFB and TBT.

Use it to investigate slow page loads, delayed interactions, layout shifts and browser tasks that block the page, across desktop and mobile experiences.

It provides reference ranges and diagnostic methods so performance work is based on measured user experience instead of guesswork.

How condevtools/pr-agent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to condevtools/pr-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/condevtools/pr-agent/main/.claude/skills/frontend-fullchain-optimization/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/condevtools/pr-agent

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/condevtools/pr-agent/frontend-fullchain-optimization/github.svg)](https://agentmods.dev/skills/condevtools/pr-agent/frontend-fullchain-optimization)

Your own site

<a href="https://agentmods.dev/skills/condevtools/pr-agent/frontend-fullchain-optimization"><img src="https://agentmods.dev/badge/skills/condevtools/pr-agent/frontend-fullchain-optimization/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/condevtools/pr-agent/frontend-fullchain-optimization"><img src="https://agentmods.dev/badge/skills/condevtools/pr-agent/frontend-fullchain-optimization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,471 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.00080	$0.05471
Opus 5.5	$0.00032	$0.02188
Sonnet 5.5	$0.00016	$0.01094
Haiku 4.5	$0.00008	$0.00547

Measured 9d ago against content hash 3b2d7580daf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 9d 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" \

.claude/skills/frontend-fullchain-optimization/SKILL.md · 520 lines

How it starts

The opening of the file, as written. The whole thing — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Full-Chain Performance Optimization Guide

A frontend performance diagnostic and optimization system based on Web Vitals core metrics. Core principle: User-centric — optimization is about doing less, not more.

Metric Threshold Quick Reference

Metric	Good	Needs Improvement	Poor	Unit	Focus
LCP	≤ 2.5s	2.5s - 4s	> 4s	Time	Largest Contentful Paint
FCP	≤ 1.8s	1.8s - 3s	> 3s	Time	First Contentful Paint
INP	≤ 200ms	200ms - 500ms	> 500ms	Time	Interaction to Next Paint
CLS	≤ 0.1	0.1 - 0.25	> 0.25	Score	Visual Stability
TTFB	≤ 800ms	800ms - 1.8s	> 1.8s	Time	Time to First Byte
FID	≤ 100ms	100ms - 300ms	> 300ms	Time	First Input Delay
TBT	Tasks > 50ms are long tasks	—	—	Time	Total Blocking Time

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.

Diagnostic Decision Tree

Page loads slowly?
├── TTFB > 800ms → Network/server issue → See "TTFB Optimization"
├── FCP > 1.8s → Resource blocking/large files → See "FCP Optimization"
├── LCP > 2.5s
│   ├── TTFB & FCP normal → Slow viewport resource loading → See "LCP Optimization"
│   └── TTFB or FCP abnormal → Fix upstream metrics first
├── INP > 200ms → Long tasks blocking main thread → See "INP Optimization"
├── CLS > 0.1 → Layout shifts → See "CLS Optimization"
└── Lighthouse Performance Score
    ├── > 80: Few issues
    ├── 60-80: Needs focused analysis, priority: FCP → LCP → CLS
    └── < 60: Severe issues, full audit required

INP Optimization (Interaction Responsiveness)

Diagnosis: Chrome Performance panel — look for long tasks (> 50ms, highlighted red); inspect event handler duration in the flame chart.

Strategy — Break long tasks into shorter ones:

Method	Mechanism	Use Case
`setTimeout(fn, 0)`	Creates a new macrotask at the end of the queue	Non-urgent network requests, DB operations
`Promise.resolve().then(fn)`	Creates a microtask, runs immediately after current macrotask	Secondary tasks needing faster execution
`requestAnimationFrame(fn)`	Runs before next repaint	Rendering-related tasks
`requestIdleCallback(fn)`	Lowest priority, runs when main thread is idle	Analytics, logging
`scheduler.postTask(fn, {priority})`	Fine-grained priority control	Scenarios requiring precise scheduling

Read the full file on GitHub · 520 lines

Changes

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.

9d ago Changed · -46 lines 3b2d7580daf9
2mo ago First seen · 566 lines · 80 tokens per session scan A 0847bef27821

Subscribe to this mod's changes

frontend-fullchain-optimization is a skill published in the GitHub repository condevtools/pr-agent (7 stars, last pushed 6d ago), licensed MIT. It adds 80 tokens to every session and 5,471 once invoked, about $0.0003 per session on Opus 5.5. 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.

Analytics and metrics Frontend agent ai-agents comments issues pull-requests

frontend-fullchain-optimization next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
frontend-fullchain-optimizationcondevtools/pr-agent	Skill	7	6d ago	MIT	A	80	Claude Code
issue-commentnearform/lastlight	Skill	44	2d ago	MIT	A	47	Claude Code, Codex
githubinitializ/forge	Skill	235	yesterday	Apache-2.0	A	15	Claude Code, Codex
issue-triagenearform/lastlight	Skill	44	2d ago	MIT	A	46	Claude Code, Codex
issue-answernearform/lastlight	Skill	44	2d ago	MIT	A	70	Claude Code, Codex
pr-commentnearform/lastlight	Skill	44	2d ago	MIT	A	41	Claude Code, Codex
github-mcpFriz-zy/ai-capability-registry	Skill	12	1mo ago	MIT	A	26	Claude Code, Codex

pr-agent: Skill for Claude Code