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 skills add TheGoat395/Codex-Skills --skill performance-budget-labgit clone --depth 1 https://github.com/TheGoat395/Codex-SkillsWrote 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/thegoat395/codex-skills/performance-budget-lab)<a href="https://agentmods.dev/skills/thegoat395/codex-skills/performance-budget-lab"><img src="https://agentmods.dev/badge/skills/thegoat395/codex-skills/performance-budget-lab/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.
<a href="https://agentmods.dev/skills/thegoat395/codex-skills/performance-budget-lab"><img src="https://agentmods.dev/badge/skills/thegoat395/codex-skills/performance-budget-lab.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00011 | $0.00378 |
| Opus 5 | $0.00005 | $0.00189 |
| Sonnet 5 | $0.00002 | $0.00076 |
| Haiku 4.5 | $0.00001 | $0.00038 |
Grade A, and why
performance-budget-lab 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 3d 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.
What it actually says
Performance Budget Lab
Use this skill to keep visually rich sites fast.
Own the budget and acceptance policy. Route measured runtime diagnosis, implementation fixes, and React/Next performance work to $performance-audit-websites.
Budget Areas
- JavaScript bundle size
- route-level code splitting
- image dimensions, formats, and lazy loading
- video poster, preload, autoplay, and reduced-data behavior
- font loading and fallback metrics
- animation cost and scroll handlers
- layout shift sources
- server rendering/static rendering choices
- caching and CDN behavior
Workflow
- Identify stack and deployment target.
- Inspect package dependencies and route structure.
- Define route, hardware/device, network/cache state and measurement method.
- Run Lighthouse or browser performance checks when feasible.
- Check Core Web Vitals risks: LCP, CLS, INP, TTFB.
- Set media/JavaScript/font budgets from the intended experience and baseline evidence.
- Prefer CSS and Motion for small interactions; reserve GSAP/R3F/video for clear value.
- Report tradeoffs honestly when visual richness costs performance.
Use Lighthouse or browser checks here to validate a budget decision, not to take ownership of deep runtime diagnosis. When the work shifts from setting thresholds to locating and repairing the bottleneck, hand off to $performance-audit-websites.
Output
Give:
- current risks
- recommended budgets
- measurement conditions and reconsideration rules
- commands run
- remaining uncertainty
Scope and evidence
Output a budget contract: route/device class, hardware, network/cache state, metric, threshold, test method and reconsideration condition. Route measured diagnosis/optimization to $performance-audit-websites; a budget-only request does not implement repairs.
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.
- 3d ago Changed · +8 lines · -34 tokens per session 7926d4920fa8
- 10d ago First seen · 42 lines · 45 tokens per session scan A 66781848cae7
performance-budget-lab is a skill published in the GitHub repository TheGoat395/Codex-Skills (122 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 378 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
design-pipeline
A build-and-test workflow for turning Figma designs into shadcn/ui components, a reusable set of interface components for React-based projects. It checks the result in a real browser at three screen sizes and runs accessibility checks.
swiftui-animation
Implement, diagnose, or review SwiftUI motion using explicit and scoped implicit animations, springs, transitions, PhaseAnimator, KeyframeAnimator, matched geometry or navigation zoom, SF Symbol effects, and custom Animation types. Use when views should animate on state changes, insertion, removal, navigation, or…
swiftui-gestures
Implement, review, or improve SwiftUI gesture handling. Use when adding tap, long press, drag, magnify, or rotate gestures, composing gestures with simultaneously/sequenced/exclusively, managing transient state with @GestureState, resolving parent/child gesture conflicts with highPriorityGesture or…
swiftui-layout-components
Build SwiftUI layouts using stacks, grids, lists, scroll views, forms, and controls. Covers VStack/HStack/ZStack, LazyVGrid/LazyHGrid, List with sections and swipe actions, ScrollView with ScrollPosition and scroll-driven reveal surfaces, Form with validation, Toggle/Picker/Slider, .searchable, and overlay patterns.…
swiftui-webkit
Embeds and controls web content in SwiftUI with WebKit for SwiftUI, including WebView, WebPage, navigation policies, JavaScript execution, observable page state, link interception, local HTML or data loading, and custom URL schemes. Use when building iOS 26+ article/detail views, help centers, in-app documentation, or…
focus-engine
Implements keyboard, directional, and scene-level focus behavior across SwiftUI and UIKit. Use when managing @FocusState, defaultFocus, focused values, focusable interactions, focus sections, tvOS geometric focus and Siri Remote navigation, watchOS Digital Crown input, visionOS connected-device focus versus gaze…