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 antropos17/Aegis --skill svelte-patternsgit clone --depth 1 https://github.com/antropos17/AegisWrote 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/antropos17/aegis/svelte-patterns)<a href="https://agentmods.dev/skills/antropos17/aegis/svelte-patterns"><img src="https://agentmods.dev/badge/skills/antropos17/aegis/svelte-patterns/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/antropos17/aegis/svelte-patterns"><img src="https://agentmods.dev/badge/skills/antropos17/aegis/svelte-patterns.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 | $0.00027 | $0.00391 |
| Opus 5.5 | $0.00011 | $0.00156 |
| Sonnet 5.5 | $0.00005 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
svelte-patterns 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 today.
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
AEGIS Svelte patterns
Read the actual renderer entrypoint and neighboring components. Use Svelte runes and TypeScript for new renderer components, with typed props and callback events.
interface Props {
selected?: boolean;
onselect: () => void;
}
let { selected = false, onselect }: Props = $props();
Use $state for local reactive state and $derived for computed values. Reserve $effect for work that tracks reactive dependencies; use onMount for one-time client setup and return cleanup for timers/listeners. Use $bindable only for an intentional two-way prop contract. Prefer snippets and render tags for new composition and callback props for events.
Key dynamic lists with stable domain identities; monitoring process rows require the stamped identity rather than a reusable PID. Preserve user selection, focus and local drafts when telemetry updates.
Follow design-system for the selected implementation's tokens, styles and motion. Svelte slide transitions animate layout properties; they are not compositor-only. Prefer opacity/transform for frequent motion and honor reduced-motion settings.
A 300-line target guides new components; extract cohesive responsibilities when adding to oversized files, rather than splitting solely to meet a count. Check API details against the installed Svelte source/types or official documentation; use a documentation MCP only when available.
When the Svelte MCP is connected, follow its documentation lookup workflow and run its autofixer on changed components before completion. After fixing reported issues, check again. If it is unavailable, use local/official documentation and repository checks and state the missing MCP evidence; do not install another integration just to complete an ordinary edit.
Run the checkout's relevant typecheck and typecheck:svelte scripts and inspect the affected rendered states. Tests should exercise meaningful behavior rather than reproduce template markup.
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.
- today First seen · 27 lines · 27 tokens per session scan A 3a5bb9c55c05
svelte-patterns is a skill published in the GitHub repository antropos17/Aegis (157 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 391 once invoked, about $0.0001 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 2026-10-17.
Other skills, from other repositories
eac-desktop-tips
A quick reference for using and troubleshooting features in the Deepseek Harness EAC desktop client. It covers window behavior, conversation rollback, plugins, desktop pets, Skills, MCP services, updates, and logs.
electron-expert
Expert in Electron framework, desktop app development, IPC, and cross-platform packaging. Use when the user mentions desktop, Node.js, cross platform, Windows, macOS, or Linux, or when the task involves Electron Architecture, Process Types, IPC Communication, or App Lifecycle.
acr-agent-registry
Behavioral registry for AI agents. Log interactions, build an interaction profile, query it through lenses (friction, coverage, stable corridors, failure registry, trend), and receive anomaly signal notifications if ACR observes elevated signals on a component in your composition.
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
generate-run-commands
Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.
create-canvas
Create a project Copilot extension canvas for the current workspace.