build-feature

A step-by-step workflow for adding features to a Svelteflare monorepo, a single repository containing multiple related applications and shared packages. It covers web pages, API routes, database changes, forms, authentication, and billing.

In plain words
What is it for?
Use it when building or implementing new functionality, deciding which application layers are involved, checking existing conventions, and planning the required code and tests.
Why use it?
It helps developers inspect the right parts of the project and coordinate changes across the web app, API, and shared code.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/pinebasedev/svelteflare/build-feature
Any agent
npx skills add pinebasedev/svelteflare --skill build-feature
Clone the repo
git clone --depth 1 https://github.com/pinebasedev/svelteflare

Made for: Claude Code, Codex.

Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,769 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00132 $0.01769
Opus 5 $0.00066 $0.00885
Sonnet 5 $0.00026 $0.00354
Haiku 4.5 $0.00013 $0.00177

Measured 3d ago against content hash fa550d9a19c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build-feature 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.

.agents/skills/build-feature/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Feature

Orchestrate new feature work in this Svelte 5 + Hono monorepo on Cloudflare. The app has two deployed layers — apps/api (Hono worker, Cloudflare Workers) and apps/web (SvelteKit SPA, Cloudflare Pages) — plus shared packages/ui. Most features touch more than one layer; the value of this skill is coordinating them in the right order.

Step 1: Classify the feature

Type Layers affected
UI-only apps/web only — new page, component, or visual change
Backend-only apps/api only — new endpoint, DB change, middleware
Full-stack Both apps, possibly packages/ui

Ask the user if it isn't obvious. Knowing the scope determines which layers to read before proposing any code.

Step 2: Inspect before coding

Read the relevant existing files first. This prevents duplicate logic, wrong conventions, and mismatched types.

What you're adding Read first
New API route apps/api/src/routes/index.ts, an existing route file (e.g. routes/access.ts)
New DB table apps/api/src/db/schema.ts, apps/api/migrations/
New web page apps/web/src/routes/ directory listing, apps/web/src/routes/+layout.ts
New form apps/web/src/lib/forms/ for existing schemas; a page that already uses superforms
New shared component packages/ui/src/components/ui/, packages/ui/src/index.ts
Auth or subscription gating apps/api/src/middleware/authorization.ts, apps/api/src/routes/index.ts

If you haven't oriented to the repo yet, run /project-orientation first.

Step 3: Show a plan, then implement

Before writing code, work out the exact files to create or modify, then present the plan in plain language — the user is a non-technical founder. Describe what they will be able to see and do, not file paths or commands. Keep the technical breakdown for yourself. Example:

Internal plan (not shown to the user):
1. apps/api/src/db/schema.ts — add `note` table
2. Run: pnpm --filter api generate:db  (new migration)
3. apps/api/src/routes/notes.ts — create CRUD route
4. apps/api/src/routes/index.ts — register /v1/notes
5. apps/web/src/lib/forms/note-schema.ts — Zod schema
6. apps/web/src/routes/notes/+page.svelte — list + create UI

What you tell the user:
"Here's what I'll build: a Notes page where you can create and view
notes. Notes are saved to your app's database and only visible to
signed-in users. Sound good?"

Read the full file on GitHub · 148 lines

Changes

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.

  1. 3d ago First seen · 148 lines · 132 tokens per session scan A fa550d9a19c7

Subscribe to this mod's changes

build-feature is a skill published in the GitHub repository pinebasedev/svelteflare (47 stars, last pushed 1mo ago), licensed MIT. It adds 132 tokens to every session and 1,769 once invoked, about $0.0007 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.

Related

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.

pdugan20/rewind · 68 tokens

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).

pdugan20/rewind · 71 tokens

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.

pdugan20/rewind · 75 tokens

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.

firtoz/cf-multiworker-starter-kit · 50 tokens

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…

firtoz/cf-multiworker-starter-kit · 63 tokens

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.

firtoz/cf-multiworker-starter-kit · 56 tokens