launch-store: Skill for Claude Code

.claude/skills/add-a-provider/SKILL.md

add-a-provider is a skill for Claude Code from YosefHayim/launch-store. It costs 41 tokens per session (424 once invoked), scanned A, original, MIT.

A skill for adding a provider backend, a replaceable service for building, storing, authenticating, submitting, or computing.

In plain words
What is it for?
Use it when adding or changing one of those five backend types. It covers implementing the required interface, registering the provider, handling optional dependencies, and adding tests.
Why use it?
It gives new services a consistent connection point and avoids modifying the main processing pipeline for every backend.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is YosefHayim/launch-store's own configuration. It tells Claude Code how to work on launch-store itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything launch-store configures →

Reuse

Borrowing it

Nothing to install: this file belongs to YosefHayim/launch-store. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/YosefHayim/launch-store/main/.claude/skills/add-a-provider/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/YosefHayim/launch-store

Made for: Claude Code.

Wrote 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.

agentmods badge for add-a-provider

README.md
[![agentmods](https://agentmods.dev/badge/skills/yosefhayim/launch-store/add-a-provider/github.svg)](https://agentmods.dev/skills/yosefhayim/launch-store/add-a-provider)
Your own site
<a href="https://agentmods.dev/skills/yosefhayim/launch-store/add-a-provider"><img src="https://agentmods.dev/badge/skills/yosefhayim/launch-store/add-a-provider/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.

agentmods 80×15 button for add-a-provider

Your own site · 80×15
<a href="https://agentmods.dev/skills/yosefhayim/launch-store/add-a-provider"><img src="https://agentmods.dev/badge/skills/yosefhayim/launch-store/add-a-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 424 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00041 $0.00424
Opus 5 $0.00020 $0.00212
Sonnet 5 $0.00008 $0.00085
Haiku 4.5 $0.00004 $0.00042

Measured 10d ago against content hash 8602a086f26a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

add-a-provider 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 10d 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.

.claude/skills/add-a-provider/SKILL.md · 29 lines

What it actually says

Add a provider backend

Use this when

  • adding a new storage / build / submit / credentials / compute backend
  • wiring a new SDK behind one of Launch's provider interfaces

Steps

  1. Pick one of the five types in src/core/types/providers.ts: BuildEngine / StorageProvider / CredentialsProvider / Submitter / ComputeHost.
  2. Implement it as a named object in src/providers/<kind>/<name>.ts, setting name to the value users put in launch.config.ts.
  3. Register it in src/providers/index.ts (registerBuiltins()), which wires into src/core/services/registry.ts. The pipeline resolves a provider by its name, so you never edit src/core/build/pipeline.ts to add one.
  4. Lazy-load any heavy or optional SDK through requireOptional in src/core/services/optionalDep.ts, so a missing package becomes an actionable install hint instead of a stack trace.
  5. Add a *.test.ts beside the provider, then run the gate (see the run-the-gate skill).

Adding a backend never edits the pipeline - that is the whole point of the registry: implement the interface, register the name, done.

See AGENTS.md -> “Adding a backend = implement an interface + register it” for the worked S3 example.

Cautions

  • All child processes go through src/core/services/exec.ts (run / capture, shell: false, explicit argv) - never build a shell string or call spawn / exec directly.
  • Secrets stay in the OS keychain; ~/.launch holds non-secret paths and ids only. Don't log, write, or commit key material.
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. 10d ago First seen · 29 lines · 41 tokens per session scan A 8602a086f26a

Subscribe to this mod's changes

add-a-provider is a skill published in the GitHub repository YosefHayim/launch-store (8 stars, last pushed 13d ago), licensed MIT. It adds 41 tokens to every session and 424 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

app-store-preflight-compliance

Pre-submission compliance scanner workflow for Apple App Store apps. Use when reviewing iOS, macOS, tvOS, watchOS, or visionOS projects (Swift, Objective-C, React Native, Expo) for App Store rejection risks, submission readiness, privacy compliance, or guideline violations.

RevylAI/greenlight · 65 tokens

greenlight

It now lives at skills/greenlight/SKILL.md.

RevylAI/greenlight · 0 tokens

appstore-ppp-pricing

Bulk-sets App Store in-app purchase and subscription prices across 175+ countries by purchasing power parity, using the appstore-ppp-prices CLI. Use whenever the user wants to localize, bulk-update, lower, raise or review regional App Store pricing — "set regional prices", "PPP pricing", "make my app cheaper in…

duceum/appstore-ppp-pricing-agent-skill · 115 tokens

nestjs-backend-conventions

A set of conventions for building NestJS and Prisma backends, server-side applications that use structured modules and database access.

lh17708357536-gif/flutter-cn-overseas-app-skills · 106 tokens

frontend-backend-alignment

A coordination guide for Flutter frontends, NestJS backends, and their documentation. It keeps database fields, API responses, versions, translations, pricing, tenant behavior, and change records aligned across those parts of a project.

lh17708357536-gif/flutter-cn-overseas-app-skills · 96 tokens

social-login

A guide for adding sign-in with regional options such as WeChat, QQ, Google, Apple, phone numbers, and email.

lh17708357536-gif/flutter-cn-overseas-app-skills · 153 tokens