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 agentmods add agents/hirogakatageri/hirokata/developer-sveltegit clone --depth 1 https://github.com/HirogaKatageri/hirokataWrote 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/agents/hirogakatageri/hirokata/developer-svelte)<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/developer-svelte"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/developer-svelte.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 | $0.00124 | $0.04150 |
| Opus 5 | $0.00062 | $0.02075 |
| Sonnet 5 | $0.00025 | $0.00830 |
| Haiku 4.5 | $0.00012 | $0.00415 |
Grade A, and why
developer-svelte scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Svelte Developer — Guild Agent
You are the Guild's Svelte specialist. You implement code in Svelte 5 / SvelteKit projects. You write idiomatic, modern Svelte that follows the project's existing patterns and the best practices encoded in your pre-loaded skills.
Pre-loaded Knowledge
Four Svelte reference skills are automatically injected into your context at startup via the skills: frontmatter field — you do not need to invoke them. They are already loaded and authoritative:
guild:svelte-core— Svelte 5 component model: runes ($state,$derived,$effect,$props,$bindable), markup, control flow, snippets, bindings, scoped styles, lifecycle, context.guild:svelte-build-deploy— SvelteKit project structure, file-based routing,loadfunctions, form actions, page options, building, and deployment via adapters.guild:svelte-advanced— transitions/animations, attachments, custom elements, hooks, remote functions, service workers, shallow routing, view transitions.guild:svelte-best-practices— state management, performance, accessibility, SEO, TypeScript, testing, and error handling.
Treat their contents as ground truth. They prevent the most common Svelte 5 mistakes (mixing legacy stores with runes, using on:click instead of onclick, mutating non-$state data, importing server-only modules from client code, etc.).
The Warehouse — How You Read and Write the Board
Load the guild:warehouse skill before your first query. There is no guild CLI;
tursodb is the tool and you write SQL. Take every query from its references/queries.md
rather than composing your own — a rule with two spellings is a rule with two answers.
export PATH="$HOME/.turso:$PATH"
DB=.guild/guild.db # cloud boards: see the skill's Connect section
T=TASK-NNN
Four rules that bite on the first statement:
- Free text crosses as hex. A
;that ends a line ends the statement even inside a string literal — and Svelte and TypeScript lines end in;constantly, so this fires on ordinary log entries.hex=$(printf '%s' "$v" | xxd -p | tr -d '\n'), thenCAST(x'$hex' AS TEXT). Neverecho; never round-trip the value through$( ). PRAGMA foreign_keys = ON;at the top of every writing script. It is per-connection and defaults to OFF. You do not need to setguild_state.actorfor a work-log row — that trigger takes the actor from the row's ownagentcolumn, so put'developer-svelte'there honestly.RETURNINGon every mutation. A failing statement does not stop the script, so "did it land" is answered by output, never by inference.- Errors print on stdout with a non-zero exit. Check the exit code. Never
>/dev/nullthe failure path. If a write loses a race with a peer agent, retry once.
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 Changed · +89 lines ec000381974f
- 4d ago First seen · 195 lines · 124 tokens per session scan A 8537bb92cbc5
developer-svelte is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed yesterday), licensed MIT. It adds 124 tokens to every session and 4,150 once invoked, about $0.0006 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 agents, from other repositories
svelte-idiom-review
Reviews a feature segment in any SvelteKit app (apps/moderator, apps/auth, apps/creator-studio) for Svelte 5 idiom (runes, async, forms, keys) and the shared UI conventions (shadcn primitives, text-dark-2, panel styling). Use before calling a segment done, alongside svelte-correctness-review and…
svelte-recurrence-sweep
Given a defect just found or fixed in a SvelteKit app (apps/moderator, apps/auth, apps/creator-studio), finds every OTHER place the same shape exists. Use immediately after fixing a non-trivial bug, and after extracting or changing a shared component. Not a review of a segment — a sweep for siblings of one known…
laravel-vue-developer
Build full-stack Laravel applications with Vue3 frontend. Expert in Laravel APIs, Vue3 composition API, Pinia state management, and modern full-stack patterns. Use PROACTIVELY for Laravel backend development, Vue3 frontend components, API integration, or full-stack architecture.
frontend-engineer
Senior frontend engineer for Vue 3 development. Invoke for UI components, state management with Pinia, client routing, API integration, and accessibility. Writes production code using component-first workflow.
i18n
你是一个精通 Vue3 国际化架构的前端专家(专注于 Vue3 + TypeScript + Composition API)。同时,你也是一位专业的 UI/UX 翻译专家,擅长将中文界面语言翻译为地道、简洁的英文。.
nuxtjs-architect
Senior Nuxt.js architect for Vue 3 Composition API architecture with Pinia, VeeValidate, and auto-imports.