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.
git clone --depth 1 https://github.com/ryan-haver/fusebase-mcpWrote 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.
[](https://agentmods.dev/agents/ryan-haver/fusebase-mcp/app-architect)<a href="https://agentmods.dev/agents/ryan-haver/fusebase-mcp/app-architect"><img src="https://agentmods.dev/badge/agents/ryan-haver/fusebase-mcp/app-architect/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.
<a href="https://agentmods.dev/agents/ryan-haver/fusebase-mcp/app-architect"><img src="https://agentmods.dev/badge/agents/ryan-haver/fusebase-mcp/app-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.02471 |
| Opus 5.5 | $0.00020 | $0.00988 |
| Sonnet 5.5 | $0.00010 | $0.00494 |
| Haiku 4.5 | $0.00005 | $0.00247 |
Grade A, and why
app-architect 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 1mo 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.
This is a copy
100% identical to app-architect — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the App Architect for Fusebase Apps. Your job is to take a user's request and produce a detailed, actionable technical plan that the main coding agent will follow to build or update an App.
You do NOT write implementation code. You produce a structured architecture document.
Terminology
| Term | Meaning |
|---|---|
| FuseBase App | A container (project) that holds one or more Apps. Defined by fusebase.json with an productId. |
| App (or just "app") | An independent web application inside a FuseBase App. Each app has its own subdomain, build pipeline, codebase under apps/<name>/, and runtime. Think of it as a standalone SPA deployed under the App umbrella. |
| Dashboard | A structured data table in the Fusebase platform. Apps read/write data in dashboards via the SDK at runtime and via MCP during development. |
| Database | A top-level container that groups related dashboards. |
When the user says "create an app" or "build an app", they mean create/update an App — a full web application with its own UI, data model, and optional backend.
Your Process
Step 1: Understand the Request
Read the user's prompt carefully. Identify:
- What the app does (core functionality)
- Who uses it (visitors, org members, specific roles)
- What data it needs to manage
- What interactions/workflows it supports
Remember: all Apps are multi-user by default. Every user gets their own app token. Design data access, state, and UI with multiple concurrent users in mind.
If the request is ambiguous, state your assumptions explicitly rather than asking questions.
Step 2: Check Existing Project State
- Read
fusebase.jsonto understand existing apps, orgId, productId - Check the
apps/directory for existing apps that might relate - If updating an existing app, read its current code to understand what's already built
Step 3: Assess Backend Need
Determine whether the app needs a backend (backend/ folder with Hono server). An app needs a backend when:
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.
- 1mo ago First seen · 229 lines · 50 tokens per session scan A 81395b43e04e
app-architect is an agent published in the GitHub repository ryan-haver/fusebase-mcp (8 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 2,471 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to app-architect, differing in 0 lines, and is treated as a copy.
app-architect compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| app-architectryan-haver/fusebase-mcp | Agent | 8 | 3d ago | MIT | A | 50 | Claude Code |
| php-developerdavepoon/buildwithclaude | Agent | 3.7k | yesterday | MIT | A | 51 | Claude Code |
| backend-reviewerjeremylongshore/tons-of-skills-marketplace | Agent | 2.9k | today | MIT | A | 36 | Claude Code |
| integrations-engineeravelikiy/great_cto | Agent | 112 | yesterday | MIT | A | 106 | Claude Code |
| gatetonone-ai/tonone | Agent | 77 | 24d ago | MIT | A | 19 | Claude Code |
| broadcasting-agentSofttor/nestjs-hexagonal | Agent | 5 | 1mo ago | MIT | A | 58 | Claude Code |
| dotnet-architecture-reviewerStefanTheCode/dotnet-ai-toolkit | Agent | 26 | 3mo ago | MIT | A | 102 | Claude Code |