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 skills/pinebasedev/svelteflare/project-orientationnpx skills add pinebasedev/svelteflare --skill project-orientationgit clone --depth 1 https://github.com/pinebasedev/svelteflareWhat 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 | $0.00087 | $0.02076 |
| Opus 5 | $0.00044 | $0.01038 |
| Sonnet 5 | $0.00017 | $0.00415 |
| Haiku 4.5 | $0.00009 | $0.00208 |
Grade A, and why
project-orientation 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.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Svelteflare — Project Orientation
This orientation is for you, the agent — don't recite it to the user. The user is a non-technical founder: when they ask about the project, translate to plain language (what the app does and where things stand, not ports, packages, or file paths). The non-negotiable UI/theme rules live in the root AGENTS.md — read them before any UI work.
Architecture
Two-layer Cloudflare stack:
| Layer | Package | Port | Tech |
|---|---|---|---|
| API | @repo/api |
9003 | Hono + Drizzle ORM + better-auth, runs as a Cloudflare Worker |
| Web | @repo/web |
9002 | SvelteKit static SPA served by a Cloudflare Worker (static assets) |
The API handles all business logic; the web app is a pure frontend that talks to the API via PUBLIC_API_URL.
Monorepo Layout
/
├── apps/
│ ├── api/ # Cloudflare Worker — auth, DB, Stripe, business logic
│ └── web/ # SvelteKit SPA — all UI and routing
├── packages/
│ ├── ui/ # Shared shadcn-svelte component library
│ ├── typescript-config/ # Shared tsconfig bases (svelte.json, worker.json)
│ └── eslint-config/ # Shared ESLint config
├── Justfile # Convenience recipes (dev, build, deploy, db, lint)
├── turbo.json # Turborepo task pipeline
└── pnpm-workspace.yaml
Package names use the @repo/* workspace alias.
Where Things Live
UI Components
- Shared library:
packages/ui/src/components/ui/(shadcn-svelte / bits-ui)- 56 components exported — read
packages/ui/src/index.tsfor the current list before building or installing anything
- 56 components exported — read
- App-specific components:
apps/web/src/lib/components/ - Add new shadcn components:
pnpm --filter @repo/ui ui:add <component-name> - Import alias:
@repo/ui→packages/ui/src(configured inapps/web/svelte.config.js) - Styling: theme tokens only (
bg-primary,text-muted-foreground, …) — no palette classes or color literals; see rootAGENTS.mdand theui-and-themeskill
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 First seen · 173 lines · 87 tokens per session scan A 16f9bc815195
project-orientation is a skill published in the GitHub repository pinebasedev/svelteflare (47 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 2,076 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
changelog-writer
This skill should be used when the user asks to "add a changelog entry", "write changelog", "audit changelog", "review changelog", "check changelog entries", or is editing docs-mintlify/changelog.mdx. Enforces a consistent, reader-facing voice and cuts implementation trivia.
add-media
This skill should be used when the user asks to "add a movie", "add a vinyl", "add to my collection", "add physical media", "add a Blu-ray", "add a CD", or "bought these records". It handles both movies (via TMDb/Trakt) and music (via Discogs).
media-search
This skill should be used when the user asks to "search for a movie", "find a record on Discogs", "look up a film", "search TMDb", "search Discogs", "what's the TMDb ID for", "what's the Discogs ID for", or wants to look up media metadata before adding it to the collection.
multiworker-workflow
Repo-root commands, typegen and typecheck cadence, lint, deploy, adding packages with bun, and Alchemy app layout. Use at the start of a task, before PR, or when choosing turbo/typegen commands.
creating-skills
Guide for creating new Agent Skills when patterns emerge or improvements are needed. Use when encountering repeated patterns, making the same mistakes, discovering better approaches, or receiving user corrections. Covers keeping each skill small (one topic), when to split SKILL.md or add references/, and line-count…
multiworker-gotchas
Fork and template gotchas (env import, routes, typegen, forms, D1, Turbo, HMR, new DO packages). Use when working on apps/web or durable-objects, or when behavior diverges from this stack’s conventions.