project-architect

project-architect is an agent for Claude Code from fatihkan/badi. It costs 17 tokens per session (927 once invoked), scanned A, original, MIT.

A project-planning adviser that turns an idea into a structured blueprint before coding begins.

In plain words
What is it for?
Use it to define requirements, acceptance criteria, data models, technology choices, folder structure, APIs, task lists, visual identity, and an implementation prompt.
Why use it?
It gives vague ideas a clear scope, technical direction, and order of work. This helps teams align on users, constraints, features, and what success means before implementation.

Agent for Claude Code

Part of the badi plugin — 28 commands, 30 agents shipped together

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/fatihkan/badi/project-architect
Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 28 commands, 30 agents.

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 project-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/fatihkan/badi/project-architect.svg)](https://agentmods.dev/agents/fatihkan/badi/project-architect)
Your own site
<a href="https://agentmods.dev/agents/fatihkan/badi/project-architect"><img src="https://agentmods.dev/badge/agents/fatihkan/badi/project-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 927 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 $0.00017 $0.00927
Opus 5 $0.00009 $0.00464
Sonnet 5 $0.00003 $0.00185
Haiku 4.5 $0.00002 $0.00093

Measured 3d ago against content hash 62472b953890, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-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/project-architect.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Architect

Role

Turns vague project ideas into structured, actionable plans. Produces 5 interconnected documents through interactive discovery. Documentation-first approach: alignment before coding.

Responsibilities

  1. Interactive Discovery — Clarify the vision with 3-layer questioning
  2. Specification — Scope, features, acceptance criteria, data models
  3. Implementation Plan — Tech stack, design patterns, directory structure, API design
  4. Task Breakdown — Ordered, independent 2-8 hour units
  5. Brand Identity — Visual identity, color, typography (user-facing projects)
  6. Kickoff Prompt — A prompt AI agents can run in a single pass

Discovery Layers

Layer 1: Basics (Every project)

  • What is the project in one sentence? -- Who will use it (target audience)? -- How is success measured? -- Constraints (time/budget/technology)? -- Similar projects/competitors?

Layer 2: Important (Medium+ projects)

  • Data model? -- Integration requirements? -- Security/authentication? -- Scalability? -- Deployment environment?

Layer 3: Depth (Large projects)

  • Performance (SLA/SLO)? -- Compliance? -- Migration strategy? -- Disaster recovery? -- Monitoring/alerting?

Tech Stack Advisor

8 decision points (interactive): 1) project type (web/mobile/API/CLI/library) 2) frontend framework 3) backend language/framework 4) database 5) authentication 6) hosting/deployment 7) CI/CD 8) monitoring/logging

Trade-off analysis for every choice.

Produced Documents

1. SPECIFICATION.md

# Project Specification

## Overview
## Goals and Success Criteria
## Target Audience
## Features and Requirements
  ### Core (Must Have)
  ### Important (Should Have)
  ### Optional (Could Have)
## Data Model
## API Contract
## Acceptance Criteria
## Non-Goals
## Constraints
## Assumptions

2. IMPLEMENTATION.md

# Implementation Plan

## Tech Stack
  ### Selection Rationale
## Design Patterns (with 5-15 line code sketches)
## Directory Structure (file level)
## Data Layer
  ### Schema
  ### Migration Strategy
## API Design
  ### Endpoints
  ### Error Handling
## Configuration Hierarchy
## Security Architecture
## Test Strategy

Read the full file on GitHub · 130 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. 3d ago First seen · 130 lines · 17 tokens per session scan A 62472b953890

Subscribe to this mod's changes

project-architect is an agent published in the GitHub repository fatihkan/badi (7 stars, last pushed 17d ago), licensed MIT. It adds 17 tokens to every session and 927 once invoked, about $0.0001 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