Agent skill

Blueprint Supabase Scaffold

by receptron in receptron/mulmoterminal

Lay out a Vue app on the local Supabase stack, served as static files by wrangler, with tests that run against the local stack.

MITAuto-check: notesAgent Workflows

Install Blueprint Supabase Scaffold

skills CLI
$ npx skills add receptron/mulmoterminal --skill blueprint-supabase-scaffold -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install receptron/mulmoterminal blueprint-supabase-scaffold --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/receptron/mulmoterminal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/blueprints/supabase/skills/scaffold .claude/skills/blueprint-supabase-scaffold && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
blueprint-supabase-scaffold
GitHub stars
237
Token cost
~1.1k tokens
SKILL.md length
460 words
Files
1
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

Lay out a Vue app on the local Supabase stack, served as static files by wrangler, with tests that run against the local stack.

  • Agent Workflows work in your project
  • Calls yarn, wrangler and supabase; needs PUBLISHABLE_KEY and VITE_SUPABASE_PUBLISHABLE_KEY

What it does

Blueprint Supabase Scaffold is an agent skill from receptron/mulmoterminal. Lay out a Vue app on the local Supabase stack, served as static files by wrangler, with tests that run against the local stack.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. It works with Supabase, Cloudflare Workers, Vue.js and TypeScript. The repository describes itself as: Run multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs you. Local, tmux-backed, MIT. The licence is MIT.

When your agent uses it

  • Agent Workflows work in your project

Example prompts

  • “/blueprint-supabase-scaffold”

Requirements

  • A credential in VITE_SUPABASE_PUBLISHABLE_KEY
  • A credential in PUBLISHABLE_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit b3f6ff0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • yarn
    • wrangler
    • supabase
    • node
    • vitest
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use yarn, wrangler, supabase and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • PUBLISHABLE_KEY
    • VITE_SUPABASE_PUBLISHABLE_KEY
    • SECRET_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Blueprint Supabase Scaffold loads about 1.1k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 460 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:18
    scripts/local-env.mjs   writes .env.development.local from the running local stack
  • NoteMentions a .env fileSKILL.md:28
    `.env.development.local` as those two variables.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from receptron/mulmoterminal at commit b3f6ff0, republished under its MIT licence (© receptron). 460 words, ~1,096 tokens.

Download SKILL.mdSave it as .claude/skills/blueprint-supabase-scaffold/SKILL.md (or your agent's skills folder).
name
blueprint-supabase-scaffold
description
Lay out a Vue app on the local Supabase stack, served as static files by wrangler, with tests that run against the local stack.

App skeleton

One folder, one package.json, TypeScript throughout, yarn. The later checks rely on this layout exactly:

supabase/config.toml    yarn supabase init; project_id is the app's name
supabase/migrations/    the schema, one timestamped .sql per change (yarn supabase migration new <name>)
supabase/seed.sql       rows for trying the app locally; the security check needs one in every table
index.html              the Vue entry (<div id="app">)
src/client/             Vue 3 + Vite; src/client/supabase.ts creates the one Supabase client
vite.config.ts          writes _headers into the build (see below)
wrangler.jsonc          serves the build as static files; there is no Worker code
scripts/local-env.mjs   writes .env.development.local from the running local stack
test/                   vitest against the local stack; one file per area: data, ui, auth
  • Dev dependencies: supabase, @supabase/supabase-js, vite, @vitejs/plugin-vue, vue, typescript@^6 (not 7: a later check reads test files through TypeScript's compiler API, which TypeScript 7 does not ship), vitest, wrangler.
  • The browser gets two values and no others: VITE_SUPABASE_URL and VITE_SUPABASE_PUBLISHABLE_KEY (the publishable key, sb_publishable_…). The secret key never goes into src/ or any VITE_ variable.
  • scripts/local-env.mjs runs yarn -s supabase status -o json and writes API_URL and PUBLISHABLE_KEY to .env.development.local as those two variables.
  • vite.config.ts: on vite build only, read VITE_SUPABASE_URL with loadEnv (throw if it is missing) and emit a _headers asset for every path: Content-Security-Policy: default-src 'self'; connect-src 'self' <that URL>; frame-ancestors 'none'; object-src 'none'; base-uri 'self', X-Content-Type-Options: nosniff, Referrer-Policy: same-origin. The CSP has to name the Supabase URL of the build it is in, or the browser blocks every call; a fixed public/_headers cannot, because the local and the production URL differ.
  • wrangler.jsonc: name, compatibility_date (a date the installed wrangler supports — about a month before today), "assets": { "directory": "./dist", "not_found_handling": "single-page-application" }. No main.
  • Scripts:
    • db:start: supabase start -x studio,imgproxy,logflare,vector,edge-runtime,realtime,mailpit,supavisor,postgres-meta && node scripts/local-env.mjs (leave out mailpit from -x if the spec signs people in by email link)
    • build: vite build --mode development — the local build, talking to the local stack
    • start: yarn -s db:start >/dev/null && yarn -s build && wrangler dev --local --ip 127.0.0.1. The checks run yarn start --port <n>, so extra arguments must reach wrangler dev.
    • test: vitest run
    • deploy: vite build --mode production && wrangler deploy
  • .gitignore: node_modules, dist, .wrangler, *.local.
  • test/local-stack.ts: reads yarn -s supabase status -o json; exports an admin client made with SECRET_KEY (tests only, never the app), a signed-out client made with PUBLISHABLE_KEY, and signedIn(), which creates a fresh user with auth.admin.createUser({ email, password, email_confirm: true }) and returns a client signed in as them. Tests never reach a hosted project.
  • Add one trivial passing test in test/ that reaches the local stack, so the harness is proven.
Show full SKILL.md (131 more words)Show less

The checks start the local stack themselves and reset its database to the migrations and the seed before testing, so a test may not rely on rows another test left behind.

Done when the check passes: the layout exists, yarn db:start starts the stack, yarn build and yarn test succeed.

Always

  • Read .blueprint/spec.md first. It is the agreed specification; do not widen it.
  • When you need a decision, ask it through the blueprint question tool and stop. Do not guess.
  • Do not run git init: a new repository loses the folder's trust and the next unattended step stops at Claude Code's trust prompt. The user adds git themselves after the build if they want it.
  • Say you are done by stopping; the executor runs the check. Do not claim success yourself.

© receptron, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in blueprints/supabase/skills/scaffold of receptron/mulmoterminal.

Open the folder on GitHubat commit b3f6ff0

Compare with similar skills

Blueprint Supabase Scaffold next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Blueprint Supabase Scaffold compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Blueprint Supabase Scaffold this skillreceptron/mulmoterminal237—~1.1kAutomated safety check: NotesMIT
Agent RecallGoldentrii/AgentRecall-X371—~5.2kAutomated safety check: NotesMIT
Init Ruleslifedever/claude-rules191—~652Automated safety check: PassMIT
Uniapp App Generate Skilljiushiwon/wg-skills114—~5kAutomated safety check: NotesApache-2.0
Architecturepikax/verter113—~5.6kAutomated safety check: PassMIT
Vue Generate Skilljiushiwon/wg-skills114—~3.1kAutomated safety check: PassApache-2.0

Similar skills

  • Agent Recall

    Goldentrii/AgentRecall-X

    Persistent compounding memory for AI agents. An agent skill from Goldentrii/AgentRecall-X.

    371 GitHub stars~5.2k tokensUpdated 13 days ago
    Agent WorkflowsAuto-check: notes
  • Init Rules

    lifedever/claude-rules

    Initialize or update CLAUDE.md coding standards for any project by auto-detecting tech stack and assembling rules from the claude-rules template library.

    191 GitHub stars~652 tokensUpdated 6 mo ago
    Agent WorkflowsAuto-check passed
  • Uniapp App Generate Skill

    jiushiwon/wg-skills

    This skill should be used when the user wants to create a standardized uni-app project for WeChat mini-program, H5, and App from scratch.

    114 GitHub stars~5k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check: notes
  • Architecture

    pikax/verter

    Verter codebase architecture: high-level module map, TypeScript packages, plugin system, CSS analysis, MCP server, static analysis types

    113 GitHub stars~5.6k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Vue Generate Skill

    jiushiwon/wg-skills

    This skill should be used when the user wants to create a standardized Vue 3 + TypeScript + Vite + Pinia project from scratch.

    114 GitHub stars~3.1k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed
  • Generate comprehensive release notes for Bit from git commits and pull requests.

    18k GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed

More from receptron/mulmoterminal

All 31 skills in this repo
  • Mulmoterminal Bug Report

    receptron/mulmoterminal

    Help desk for "MulmoTerminal is broken". An agent skill from receptron/mulmoterminal.

    238 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Mulmoterminal Decisions

    receptron/mulmoterminal

    Check what this project's humans have already been asked, and how they answered, before asking them something similar.

    238 GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Mulmoterminal Help

    receptron/mulmoterminal

    Help desk for questions about MulmoTerminal itself — what it can do, how a feature or a part of the screen works, how to set something up, what is new in this version or in the latest one.

    238 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Mulmoterminal Notify

    receptron/mulmoterminal

    Decide which moments MulmoTerminal beeps or pushes for, and what each one plays — soundKinds, sounds and pushKinds in ~/.mulmoterminal/config.json, plus a per-project sound / sounds in…

    238 GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Mulmoterminal Theme

    receptron/mulmoterminal

    Build a colour scheme of your own for MulmoTerminal — one that joins Midnight, Nord, Daylight and Solarized in Settings' theme picker and can then be pinned per project.

    238 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Blueprint Ask Answer

    receptron/mulmoterminal

    Answer each question from the named documents only, quoting where the answer is written, or saying plainly that the documents do not say — changing nothing yet.

    238 GitHub stars~780 tokensUpdated today
    Auto-check passed

Categories

Questions about Blueprint Supabase Scaffold

What does Blueprint Supabase Scaffold do?

Lay out a Vue app on the local Supabase stack, served as static files by wrangler, with tests that run against the local stack. Blueprint Supabase Scaffold is an agent skill from receptron/mulmoterminal. Lay out a Vue app on the local Supabase stack, served as static files by wrangler, with tests that run against the local stack.

When should I use Blueprint Supabase Scaffold?

Blueprint Supabase Scaffold fits situations like: agent Workflows work in your project.

How do I install Blueprint Supabase Scaffold in Claude Code?

Run `npx skills add receptron/mulmoterminal --skill blueprint-supabase-scaffold -a claude-code`. Or copy the skill folder (blueprints/supabase/skills/scaffold in receptron/mulmoterminal) into .claude/skills/blueprint-supabase-scaffold in your project. Claude Code loads it when a task matches its description.

How do I install Blueprint Supabase Scaffold in Codex?

Run `npx skills add receptron/mulmoterminal --skill blueprint-supabase-scaffold -a codex`. Or copy the skill folder (blueprints/supabase/skills/scaffold in receptron/mulmoterminal) into .agents/skills/blueprint-supabase-scaffold in your project. Codex loads it when a task matches its description.

Can I use Blueprint Supabase Scaffold in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add receptron/mulmoterminal --skill blueprint-supabase-scaffold -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/blueprint-supabase-scaffold, .gemini/skills/blueprint-supabase-scaffold, .github/skills/blueprint-supabase-scaffold and .opencode/skills/blueprint-supabase-scaffold in your project.

What does Blueprint Supabase Scaffold need to run?

Going by SKILL.md and its folder, Blueprint Supabase Scaffold needs the command-line tools its instructions call (yarn, wrangler, supabase, node, vitest and git) and credentials named PUBLISHABLE_KEY, VITE_SUPABASE_PUBLISHABLE_KEY and SECRET_KEY. Our summary lists: A credential in VITE_SUPABASE_PUBLISHABLE_KEY; A credential in PUBLISHABLE_KEY.

Does Blueprint Supabase Scaffold access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Blueprint Supabase Scaffold safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Blueprint Supabase Scaffold use?

Blueprint Supabase Scaffold is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Blueprint Supabase Scaffold use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Blueprint Supabase Scaffold?

Skills that share tags, products or a category with Blueprint Supabase Scaffold: Agent Recall (Goldentrii/AgentRecall-X, 371 stars), Init Rules (lifedever/claude-rules, 191 stars), Uniapp App Generate Skill (jiushiwon/wg-skills, 114 stars) and Architecture (pikax/verter, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Blueprint Supabase Scaffold?

receptron (a GitHub organization) maintains it in receptron/mulmoterminal, which has 237 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 10, 2026.

Source: receptron/mulmoterminal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.