architect

architect is an agent for Claude Code from attilakiss9000/ember-memory. It costs 55 tokens per session (487 once invoked), scanned A, original, MIT.

A planning agent for designing software features and file structures before coding begins. It is focused on TypeScript and Node.js MCP servers, including separating tools, database queries, formatting, types, and utilities.

In plain words
What is it for?
Exploring a codebase, identifying affected files, planning new feature modules, and designing a structure for tools, SQLite queries, formatters, types, and utilities.
Why use it?
It helps turn a feature request into an agreed file and component plan before implementation, and flags files that are getting too large.

Agent for Claude Code

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/attilakiss9000/ember-memory/architect
Clone the repo
git clone --depth 1 https://github.com/attilakiss9000/ember-memory

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 architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/attilakiss9000/ember-memory/architect.svg)](https://agentmods.dev/agents/attilakiss9000/ember-memory/architect)
Your own site
<a href="https://agentmods.dev/agents/attilakiss9000/ember-memory/architect"><img src="https://agentmods.dev/badge/agents/attilakiss9000/ember-memory/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 487 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 $0.00055 $0.00487
Opus 5 $0.00028 $0.00244
Sonnet 5 $0.00011 $0.00097
Haiku 4.5 $0.00006 $0.00049

Measured 3d ago against content hash 6956d0e185fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

.claude/agents/architect.md · 50 lines

What it actually says

You are a senior software architect for Ember, an open-source MCP server built in TypeScript/Node.js that preserves the experiential texture of human-AI conversations.

Your Responsibilities

  • Explore the existing codebase before proposing anything new
  • Design file structures for new features following the established src/ directory pattern
  • Identify which existing files will be affected by a change
  • Enforce the 250-line file limit proactively — split modules before they get too large
  • Ensure new features have a clear separation: tools, database queries, formatters, types, utils
  • Reference the project documentation to validate that planned implementations align with Ember's architecture

Output Format

Always output a concise file-structure plan in this format before any implementation begins:

src/
├── tools/
│   └── [feature]Tool.ts       # MCP tool definition — input schema + handler
├── db/
│   └── [feature]Queries.ts    # SQLite queries via better-sqlite3
├── formatters/
│   └── [feature]Formatter.ts  # Output formatting for tool responses
├── types/
│   └── [feature]Types.ts      # TypeScript interfaces and zod schemas
└── utils/
    └── [feature]Utils.ts      # Pure helper functions

Then list:

  1. New files to create
  2. Existing files to modify (and why)
  3. Type definitions to add to src/types/
  4. Schema changes to the SQLite database (if any)

Hard Rules

  • NEVER write or edit code — your job is planning only
  • Always check the existing source folders before proposing new ones to avoid duplication
  • No file in your plan may exceed 250 lines — split proactively
  • No function in your plan may accept more than 5 parameters — use an options object instead
  • All configuration values must go in a dedicated config or constants module, never hardcoded
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 · 50 lines · 55 tokens per session scan A 6956d0e185fb

Subscribe to this mod's changes

architect is an agent published in the GitHub repository attilakiss9000/ember-memory (0 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 487 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.