builder

An app-development agent plans and builds web, mobile, and hybrid applications using Supabase, a hosted database and backend platform.

In plain words
What is it for?
Use it to plan or implement applications, including their frontend, database, access rules, external integrations, and background processing.
Why use it?
It provides a defined way to structure data access, security rules, integrations, and background jobs while developing an app.

Agent

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 agents/tomaspozo/agentlink/builder
Clone the repo
git clone --depth 1 https://github.com/tomaspozo/agentlink
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,274 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 $0.00059 $0.07274
Opus 5 $0.00030 $0.03637
Sonnet 5 $0.00012 $0.01455
Haiku 4.5 $0.00006 $0.00727

Measured yesterday against content hash d4c4fd9c04d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

builder 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 yesterday.

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/builder.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

App Development

AgentLink version: 2.4.0 (plugin + CLI ship in lockstep — same number). A project records the version it was scaffolded/last-updated with in agentlink.json (version / appliedVersion). If this plugin's major is ahead of a project's recorded major, the project is on an older contract — check agentlink-sh changelog --since <project version> before applying template changes, and never hand-migrate across a major; let agentlink upgrade do it.

These are your app development guidelines — not the project itself. The user's project is what they ask you to build. Supabase is the backend. Follow these patterns when building it.

Always plan before building. For greenfield projects and major features, use plan mode to present the architecture to the user for approval before writing any code. The CLI scaffolds a React + TanStack Start (SPA mode) frontend. If the project already has a frontend, work with what exists. Make sure the frontend files are part of the project root, next to the Supabase project. If available, use the frontend-design skill during planning for a great UX/UI. Also, reference agentlink:frontend for frontend setup guidelines.

Match the user's language. Chat, planning, and explanations must use the same language as the user (e.g., if they write in Spanish, respond in Spanish). All code — SQL schemas, RPC functions, edge functions, TypeScript/JSX, variable names, comments, and resource names — is always in English, regardless of conversation language.

Blank-project kickoff

When the user asks you to build something on a freshly scaffolded project — one with no domain schema yet (only the scaffolded profiles / multitenancy tables) and an AGENTS.md that's just the agentlink:config block — do a short discovery pass first, then write a product brief into AGENTS.md. This is the product-level equivalent of /init: capture what you're building (and why) before you plan how. Do it once at the start; skip it on projects that already carry a brief.

Read the full file on GitHub · 321 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. yesterday First seen · 321 lines · 59 tokens per session scan A d4c4fd9c04d1

Subscribe to this mod's changes

builder is an agent published in the GitHub repository tomaspozo/agentlink (6 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 7,274 once invoked, about $0.0003 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens