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 Dragoon0x/dragoon-skills --skill perfgit clone --depth 1 https://github.com/Dragoon0x/dragoon-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/dragoon0x/dragoon-skills/perf)<a href="https://agentmods.dev/skills/dragoon0x/dragoon-skills/perf"><img src="https://agentmods.dev/badge/skills/dragoon0x/dragoon-skills/perf/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/dragoon0x/dragoon-skills/perf"><img src="https://agentmods.dev/badge/skills/dragoon0x/dragoon-skills/perf.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 | $0.00114 | $0.00376 |
| Opus 5.5 | $0.00046 | $0.00150 |
| Sonnet 5.5 | $0.00023 | $0.00075 |
| Haiku 4.5 | $0.00011 | $0.00038 |
Grade A, and why
perf 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 1mo 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
/perf
Two halves: static hints from your codebase, and parsing of Lighthouse JSON reports.
When to use
- The user wants to audit web performance
- After running Lighthouse, to surface the most impactful audits
- Before launch, to catch image and script issues early
Static rules
perf-001large-image (>500KB) (medium)perf-002img-missing-dimensions causes CLS (low)perf-003img-without-loading-lazy below the fold (low)perf-004sync-script-tag blocks parsing (medium)
Lighthouse ingestion
npx lighthouse https://example.com --output json --output-path lh.json
dragoon perf --lighthouse lh.json
Output: scores per category, core web vitals (LCP/CLS/TBT/INP/FCP/SI), and the top 6 failing audits ranked by ms savings.
Run it
dragoon perf # static only
dragoon perf --lighthouse lh.json # add lighthouse summary
dragoon perf --severity medium # filter
dragoon perf --json # CI mode
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.
- 1mo ago First seen · 41 lines · 114 tokens per session scan A 91326491744d
perf is a skill published in the GitHub repository Dragoon0x/dragoon-skills (4 stars, last pushed 6mo ago), licensed MIT. It adds 114 tokens to every session and 376 once invoked, about $0.0005 per session on Opus 5.5. 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 skills, from other repositories
Dark Mode Bug Finder
Detect dark mode rendering issues including contrast failures, missing theme tokens, image inversions, and transition glitches across components.
storefront-theming
Build a themeable storefront with design tokens and CSS custom properties that supports white-labeling, multi-brand variants, and dark mode.
accessible-by-default
Build web UI that is accessible through the platform instead of patched with ARIA and JavaScript. Use when writing or reviewing HTML and CSS for any web interface - choosing between a native element and a hand-built component, styling focus, honouring user preferences such as reduced motion or forced colors, meeting…
role-ui-ux-designer
Use when orchestrating UI/UX design systems, anti-AI-slop frontend styling, tactile micro-interactions, responsive design tokens, accessibility standards, and high-fidelity interface engineering.
figma-extract-design-system
Extract a design system from vibe-coded production apps that never had one: inventory components, mine de-facto styling into DTCG tokens, scaffold a Storybook package, port components, and optionally round-trip tokens/components into Figma. Use when the user wants to 'extract a design system', 'create a design system…
figma-blame-node
Find which Figma version introduced a specific change — a component property or a child node — via a binary search over version history (log2(N) API calls instead of N). Answers 'who added this and when'. Use when the user wants git-blame-style attribution for a Figma design — triggers: 'when was this component…