agentmods.dev

architect

A project-planning command that turns an early idea into five documents: a specification, implementation plan, task list, brand identity, and kickoff prompt.

In plain words
What is it for?
Use it when starting a small, medium, or large software project. It helps define requirements, choose a technology stack, plan tasks, and prepare the project kickoff.
Why use it?
It gives an unstructured idea a clearer scope, technical direction, and sequence of work before implementation begins. It also asks questions based on the project's estimated size.

Command for Claude Code

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

7 16d ago A scan 0 tokens original MIT
View the source file fatihkan/badi
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 commands/fatihkan/badi/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.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 644 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 $0.00000 $0.00644
Opus 5 $0.00000 $0.00322
Sonnet 5 $0.00000 $0.00129
Haiku 4.5 $0.00000 $0.00064

Measured 2d ago against content hash 2d08bebdf07e, 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 2d 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/commands/architect.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project planning command. Turns vague project ideas into 5 structured documents: specification, implementation plan, task list, brand identity, and a kickoff prompt.

Required Tools

  • Read (reference files, existing project info)
  • Write (5 documents + TaskBoard integration)
  • Agent (project-architect agent)
  • Bash (project analysis)

Procedure (7 Steps)

Step 1: Get the Project Idea

Ask the user to describe the project:

  • The project idea (1-2 sentences is enough, raw is fine)
  • Size estimate: Small (weekend) / Medium / Large

Step 2: Activate the Project-Architect Agent

Delegate to the agent:

  • Pass the project idea
  • Pick the question layer by the size estimate
  • Start the interactive discovery (Layer 1-3 questions)

Step 3: Load the References

The agent reads these reference files:

  • .claude/references/design-patterns.md
  • .claude/references/specification-guide.md
  • .claude/references/implementation-guide.md
  • .claude/references/tasks-guide.md
  • .claude/references/tech-stacks.md
  • .claude/references/elicitation-guide.md

Step 4: Tech Stack Selection

Interactive tech-stack advisory:

  • Offer options at 8 decision points
  • Show pros/cons for each option
  • Get the user's approval

Step 5: Create the 5 Documents

Create in order:

  1. docs/SPECIFICATION.md — Scope, features, acceptance criteria
  2. docs/IMPLEMENTATION.md — Tech stack, patterns, directory structure
  3. docs/TASKS.md — Ordered task list (by phase)
  4. docs/BRANDING.md — Visual identity (user-facing projects)
  5. docs/PROMPT.md — A single-pass kickoff prompt

Step 6: Badi Integration

Integrate the produced documents into the Badi system:

  • Move tasks from TASKS.md into .claude/workspace/TaskBoard.md
  • Nominate the key architecture decisions from IMPLEMENTATION.md into knowledge-base.md
  • Add the SPECIFICATION.md summary to memory.md

Step 7: Next Steps

Point the user to:

  • /scaffold to build the project structure (from IMPLEMENTATION.md)
  • /start to begin the development session
  • /spec-check for conformance checks (during development)

Read the full file on GitHub · 80 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. 2d ago First seen · 80 lines · 0 tokens per session scan A 2d08bebdf07e

Subscribe to this mod's changes

architect is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 644 tokens. 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.

Planningagentsai-workflowclaude-codeclideveloper-toolshooks
Related

Other commands, from other repositories

audit-agents-skills

Audit quality of agents, skills, and commands in a Claude Code project.

FlorianBruniaux/claude-code-plugins · 20 tokens

sonarqube

Analyze SonarCloud quality issues for a specific PR.

FlorianBruniaux/claude-code-plugins · 14 tokens

land-and-deploy

Merge PR, wait for CI, verify deploy, run canary — the complete landing pipeline.

FlorianBruniaux/claude-code-plugins · 23 tokens

methodology-advisor

Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.

FlorianBruniaux/claude-code-plugins · 25 tokens

scaffold

Interactive coach that asks 4-5 questions to determine whether you need an agent, command, skill, hook, or rule — then generates a ready-to-use template. Usage: /scaffold (no arguments — starts the coaching session).

FlorianBruniaux/claude-code-plugins · 51 tokens

investigate

Systematic root-cause debugging — find the cause before writing any fix.

FlorianBruniaux/claude-code-plugins · 17 tokens