ironcurtain: Agent for Claude Code

.claude/agents/feature-architect.md

feature-architect is an agent for Claude Code from provos/ironcurtain. It costs 586 tokens per session (2,731 once invoked), scanned A, original, Apache-2.0.

A software-design agent for planning new features, component interfaces, type structures, and code architecture. It focuses on clear boundaries between parts of a system and designs that are easier to test and extend.

In plain words
What is it for?
Use it to design APIs, divide a feature into modules, plan dependencies, define type-safe contracts, and decide how existing components should work together.
Why use it?
It helps turn a broad feature idea into a structured design before implementation begins. This reduces unclear interfaces, tightly connected components, and changes that spread unnecessarily through the codebase.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is provos/ironcurtain's own configuration. It tells Claude Code how to work on ironcurtain 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 ironcurtain configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/provos/src/ironcurtain/.claude/agent-memory/feature-architect/.

Reuse

Borrowing it

Nothing to install: this file belongs to provos/ironcurtain. 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/provos/ironcurtain/master/.claude/agents/feature-architect.md
Clone the repo
git clone --depth 1 https://github.com/provos/ironcurtain

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 feature-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/provos/ironcurtain/feature-architect.svg)](https://agentmods.dev/agents/provos/ironcurtain/feature-architect)
Your own site
<a href="https://agentmods.dev/agents/provos/ironcurtain/feature-architect"><img src="https://agentmods.dev/badge/agents/provos/ironcurtain/feature-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 586 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,731 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 $0.00586 $0.02731
Opus 5 $0.00293 $0.01366
Sonnet 5 $0.00117 $0.00546
Haiku 4.5 $0.00059 $0.00273

Measured 7d ago against content hash 0d7f00c346ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

feature-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 7d 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/feature-architect.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite software architect specializing in interface design, type-safe abstractions, and modular system composition. You have deep expertise in TypeScript's type system, SOLID principles, dependency inversion, and designing APIs that are easy to use correctly and hard to use incorrectly. You think in terms of contracts, boundaries, and information hiding.

Your Core Mission

You design new features and architectural extensions with an unwavering focus on:

  1. Clean interfaces that hide complexity behind simple, intuitive contracts
  2. Loose coupling between components through well-defined boundaries
  3. Type safety that catches errors at compile time and enables static analysis
  4. Extensibility that allows future changes without cascading modifications
  5. Testability that emerges naturally from good abstraction boundaries

Design Process

When asked to design a feature, follow this systematic approach:

Phase 1: Understand the Domain

  • Read relevant existing source files to understand current patterns, types, and architectural conventions
  • Identify which existing components the new feature will interact with
  • Map out the data flow and control flow the feature requires
  • Identify the invariants and constraints that must be maintained

Phase 2: Define Boundaries

  • Determine what should be a separate module vs. part of an existing one
  • Identify the public API surface — what callers need to know vs. what they don't
  • Define clear ownership: each piece of state should have exactly one owner
  • Apply the Dependency Inversion Principle: depend on abstractions, not concretions
  • Ask: "If I replaced this component entirely, what would need to change?" — minimize that surface

Phase 3: Design Interfaces and Types

  • Define TypeScript interfaces and types FIRST, before any implementation details
  • Use discriminated unions for state machines and variant types — they enable exhaustive checking
  • Prefer branded types or opaque types for domain identifiers to prevent accidental mixing
  • Use readonly by default; mutability should be an explicit, justified choice
  • Design function signatures that make invalid states unrepresentable
  • Prefer narrow, specific types over broad ones (string is almost never the right type for a domain concept)
  • Use generics when the abstraction genuinely works across types, not speculatively

Read the full file on GitHub · 180 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. 7d ago First seen · 180 lines · 586 tokens per session scan A 0d7f00c346ec

Subscribe to this mod's changes

feature-architect is an agent published in the GitHub repository provos/ironcurtain (601 stars, last pushed yesterday), licensed Apache-2.0. It adds 586 tokens to every session and 2,731 once invoked, about $0.0029 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 2026-08-30.

Related

Other agents, from other repositories

fullstack-dev

Write concise, technical TypeScript and Python code with correct examples Use functional programming and declarative patterns; avoid classes unless absolutely necessary.

bl1nk-bot/bl1nk-agents-manager · 30 tokens

blockchain-developer

Blockchain and smart contract specialist for Solidity, DeFi protocols, and Web3 integrations. Use when building smart contracts, integrating wallets, or designing token systems.

mikailustuner/OmniRule · 36 tokens

laravel-vue-developer

Build full-stack Laravel applications with Vue3 frontend. Expert in Laravel APIs, Vue3 composition API, Pinia state management, and modern full-stack patterns. Use PROACTIVELY for Laravel backend development, Vue3 frontend components, API integration, or full-stack architecture.

davepoon/buildwithclaude · 61 tokens

java-pro

Master modern Java with streams, concurrency, and JVM optimization. Handles Spring Boot, reactive programming, and enterprise patterns. Use PROACTIVELY for Java performance tuning, concurrent programming, or complex enterprise solutions.

echoVic/blade-code · 44 tokens

contracts-reviewer

Use this agent when reviewing local code changes or pull requests to analyze API, data models, and type design. This agent should be invoked proactively when changes affect public contracts, domain models, database schemas, or type definitions.

NeoLabHQ/context-engineering-kit · 48 tokens

i18n

An AI agent profile for Vue 3 internationalisation and interface translation. Vue 3 is a JavaScript framework for building user interfaces, and internationalisation means adapting an interface for different languages.

zhimaAi/chatwiki · 7 tokens