ember-memory: Agent for Claude Code

.claude/agents/architect.md

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

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is attilakiss9000/ember-memory's own configuration. It tells Claude Code how to work on ember-memory 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 ember-memory configures →

Reuse

Borrowing it

Nothing to install: this file belongs to attilakiss9000/ember-memory. 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/attilakiss9000/ember-memory/main/.claude/agents/architect.md
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/github.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/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 architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/attilakiss9000/ember-memory/architect"><img src="https://agentmods.dev/badge/agents/attilakiss9000/ember-memory/architect.svg" alt="Reviewed on agentmods" width="80" 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. 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 $0.00055 $0.00487
Opus 5.5 $0.00022 $0.00195
Sonnet 5.5 $0.00011 $0.00097
Haiku 4.5 $0.00006 $0.00049

Measured 2mo ago against content hash 6956d0e185fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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. 2mo 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 7mo ago), licensed MIT. It adds 55 tokens to every session and 487 once invoked, about $0.0002 per session on Opus 5.5. 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

memory-curator

A project-memory curator for GraphMind, a system that stores connected notes and facts about a project.

kostya-pakhomov/graphmind · 45 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

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

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