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.
git clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/commands/perniemann/pncore/pn-audit-performance-fe)<a href="https://agentmods.dev/commands/perniemann/pncore/pn-audit-performance-fe"><img src="https://agentmods.dev/badge/commands/perniemann/pncore/pn-audit-performance-fe/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/commands/perniemann/pncore/pn-audit-performance-fe"><img src="https://agentmods.dev/badge/commands/perniemann/pncore/pn-audit-performance-fe.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00044 | $0.00630 |
| Opus 5 | $0.00022 | $0.00315 |
| Sonnet 5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
pn-audit-performance-fe 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 7d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pn-audit-performance-fe
Start every response with: [pn-command] 🔺
Advanced (palette-hidden). Not in the
/slash palette. Invoked by the/pn-frontend-auditumbrella, or directly viaget_command("pn-audit-performance-fe").
Focused frontend performance pass: audit Core Web Vitals compliance, bundle composition, image strategy, render-blocking resources, and page-type budgets. No backend performance (use pn-audit-performance) — frontend only.
Flow
1. Context
Check .pncore-stack.md for framework (Next.js / Vite / Remix / etc.). Ask if scope unclear: "Which pages to audit? (landing / app shell / all routes)"
2. Audit
Load get_skill("pn-frontend-design-philosophy") for the performance budget framework (Phase 6).
Core Web Vitals targets:
- LCP < 2.5s (largest contentful paint)
- CLS < 0.1 (cumulative layout shift — reserved image dimensions?)
- INP < 200ms (interaction to next paint)
Bundle:
- Total JS budget per page type:
- Landing/marketing: ≤ 150 KB compressed JS
- App shell: ≤ 400 KB
- Feature route: ≤ 250 KB
- Code-split by route? Dynamic
import()for heavy components? - Tree-shaking effective (no full library imports, e.g.
import _ from 'lodash')?
Images:
- Modern formats (WebP / AVIF) in use?
<img loading="lazy">for below-fold?widthandheightattributes set (prevents CLS)?- Hero images served at correct resolution (no 4K images for 400px containers)?
Render-blocking:
- No synchronous
<script>in<head>withoutdefer/async? - Critical CSS inlined or preloaded?
- Fonts preloaded with
<link rel="preload">?
Caching:
- Static assets have content-hash in filename (long
Cache-Control)? - API responses cached appropriately (stale-while-revalidate)?
Output: numbered issues table (location | issue | impact | suggested fix). Save to docs/audits/.
Gate: Present issues for triage. Apply fixes after confirmation.
3. Fix
Apply in impact order: images → render-blocking → bundle splitting → caching.
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.
- 7d ago First seen · 68 lines · 44 tokens per session scan A b440371e0f29
pn-audit-performance-fe is a command published in the GitHub repository perniemann/pnCore (0 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 630 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 2026-08-31.
Other commands, from other repositories
cost-optimize
You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud spending, identify savings opportunities, and implement cost-effective architectures across AWS, Azure, GCP, and OCI. Where provider-specific code appears below, adapt…
t800-start
A single command for creating or updating development helpers such as rules, skills, commands, subagents, and hooks. It can target a plugin, the current project, or shared settings.
t800-fix
A command for making a narrow, predefined fix to existing agents, skills, commands, rules, or hooks. A fix-pack is a file listing the exact changes to make.
t-800-factory
A command that delegates creation or integration of a subagent to the T-800 Factory. It passes the proposed role, category, permissions, callers, and existing registry information to that factory.
stripe-backend
Centralized LLM prompt instructions for Copilot and Cursor, including scripts to convert and sync rules for Python, React, Shell, and TypeScript. Designed for rapid reuse and contribution across projects.
t-800-health
bash scripts/health-check.sh.