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 helderberto/agent-skills --skill perf-auditgit clone --depth 1 https://github.com/helderberto/agent-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/helderberto/agent-skills/perf-audit)<a href="https://agentmods.dev/skills/helderberto/agent-skills/perf-audit"><img src="https://agentmods.dev/badge/skills/helderberto/agent-skills/perf-audit.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 5.1 | $0.00081 | $0.00522 |
| Opus 5 | $0.00041 | $0.00261 |
| Sonnet 5 | $0.00016 | $0.00104 |
| Haiku 4.5 | $0.00008 | $0.00052 |
Grade A, and why
perf-audit 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 Audit
Workflow
-
Detect build tool from
package.json(vite, webpack, next, rollup) -
Run the production build via the project's task runner (auto-detect from package.json).
-
Analyze the build output — non-interactive only. Never launch a browser or a long-running server in an audit; those hang an automated run. Prefer, in order:
- Measure the emitted files directly: for each file in the output dir (e.g.
dist/assets/*.js), report raw + gzipped size —gzip -c <file> | wc -c. This always works and needs no extra tooling. - Per-module breakdown, as a static artifact (not a server):
- Vite/Rollup:
npx source-map-explorer 'dist/assets/*.js', or addrollup-plugin-visualizerconfigured to emit JSON/HTML to a file - webpack/Next.js:
npx webpack-bundle-analyzer -m static -r report.html <stats-file>(writes a file; do not use the default server mode)
- Vite/Rollup:
npx vite-bundle-visualizeropens a browser and blocks — only suggest it to the user for manual exploration; do not run it here.
- Measure the emitted files directly: for each file in the output dir (e.g.
-
Check
package.jsonfor known heavy packages -
Report findings with size impact
Compare against standard industry thresholds; report gzipped sizes.
Output format
- Bundle summary: total size / gzipped size vs budget
- Large chunks: name + size + % of total
- Heavy deps: package + size + lighter alternative
- Quick wins: sorted by estimated savings
Rules
- Report gzipped sizes (what the browser downloads)
- Never auto-change dependencies -- report and suggest only
Error Handling
- Build fails -- report the error and stop; fix build issues before auditing
- No build output found -- run production build first
- Build tool unrecognized -- fall back to scanning
package.jsonfor heavy packages only
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 · +19 tokens per session 84ea7fab0ec6
- 7d ago First seen · 41 lines · 62 tokens per session scan A 86033bc57ae5
perf-audit is a skill published in the GitHub repository helderberto/agent-skills (14 stars, last pushed 5d ago), licensed MIT. It adds 81 tokens to every session and 522 once invoked, about $0.0004 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
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
flutter-development
Cross-platform development with Flutter and Dart for iOS, Android, Web, Desktop, and embedded. Use when building Flutter apps, implementing Material/Cupertino design, or optimizing Dart code.
electron-desktop
Desktop application development with Electron for Windows, macOS, and Linux. Use when building cross-platform desktop apps, implementing native OS features, or packaging web apps for desktop.
generic-react-ux-designer
Professional UI/UX design expertise for React applications. Covers design thinking, user psychology (Hick's/Fitts's/Jakob's Law), visual hierarchy, interaction patterns, accessibility, performance-driven design, and design critique. Use when designing features, improving UX, solving user problems, or conducting design…
generic-react-feature-developer
Guide feature development for React applications with architecture focus. Covers Zustand/Redux patterns, IndexedDB usage, component systems, lazy loading strategies, and seamless integration. Use when adding new features, refactoring existing code, or planning major changes.
frontend-enhancer
This skill should be used when enhancing the visual design and aesthetics of web applications. It provides modern UI components, design patterns, color palettes, animations, and layout templates. REQUIRES ui-research skill first. Use this skill for tasks like improving styling, creating responsive designs…