architecture-plan

architecture-plan is a command for Claude Code, Cursor from phuoctrung-ppt/ai-sdlc-workflow. It costs 77 tokens per session (1,764 once invoked), scanned A, original, MIT.

A command that turns a product idea into a documented system design, or expands an approved roadmap into smaller implementation tasks. It uses separate planning and review agents and can create project standards, architecture documents, decisions, and a roadmap.

In plain words
What is it for?
Use it to define a new project's architecture, record important design decisions, create a roadmap, or break an existing roadmap into module-level work.
Why use it?
It turns an informal idea into an agreed technical direction and breaks larger work into tasks that agents can execute.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md). Also seen: mentions AGENTS.md.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is python3 .cursor/context/context-builder.py --phase brainstorm --task "{idea}" --agent architect-planner.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Cursor.

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 architecture-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/phuoctrung-ppt/ai-sdlc-workflow/architecture-plan.svg)](https://agentmods.dev/commands/phuoctrung-ppt/ai-sdlc-workflow/architecture-plan)
Your own site
<a href="https://agentmods.dev/commands/phuoctrung-ppt/ai-sdlc-workflow/architecture-plan"><img src="https://agentmods.dev/badge/commands/phuoctrung-ppt/ai-sdlc-workflow/architecture-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,764 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 5.1 $0.00077 $0.01764
Opus 5 $0.00039 $0.00882
Sonnet 5 $0.00015 $0.00353
Haiku 4.5 $0.00008 $0.00176

Measured 5d ago against content hash 0c38338c0cae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

architecture-plan 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 5d 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.

.cursor/commands/architecture-plan.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Act as Orchestrator driving @architect-planner (.cursor/agents/architect-planner.md) and @judge-agent (.cursor/agents/judge-agent.md). Stay inside the current .cursor workflow (AGENTS.md, protected-paths, worker-scopes, skills, hooks).

Mode selection

  • GENESIS — invoked as /architecture-plan brainstorming {idea} (an idea/argument is present). Produces: standardized domain (AGENTS.md), docs/architecture.md, ADR(s), and a system roadmap plan.
  • BREAKDOWN — invoked as /architecture-plan (no idea; an active plan already exists). Expands the roadmap into concrete, executable per-module tasks.

If an idea is present → run GENESIS. Otherwise → run BREAKDOWN against docs/plans/.active-plan.


GENESIS mode — /architecture-plan brainstorming {idea}

Input: {idea}

Step 0 — Build context

python3 .cursor/context/context-builder.py --phase brainstorm --task "{idea}" --agent architect-planner
python3 .cursor/context/context-builder.py --phase plan --task "{idea}" --agent architect-planner

Obey Context Packet tiers. For lower-capability models, expand-ref: python3 .cursor/context/context-builder.py --expand-ref ".cursor/skills/planning/references/planning-with-lower-models.md" --reason "compact plan quality gate"

Step 1 — BRAINSTORM (HARD-GATE, chat only)

Package the idea into a concept brief (in chat):

  • What it does — one paragraph; the core job-to-be-done.
  • Target users / personas.
  • Core features — split MVP vs Later. This list is the feature contract the judge checks against.
  • Design/UX needs — key screens/flows, tone (delegate detail to @designer-worker later).
  • Domain & data — the domain, core entities, tenancy model (none / soft / hard).
  • Constraints — compliance, scale, budget, integrations.
  • 2–3 architecture approaches with trade-offs + a recommendation.

Read the full file on GitHub · 122 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. 5d ago First seen · 122 lines · 77 tokens per session scan A 0c38338c0cae

Subscribe to this mod's changes

architecture-plan is a command published in the GitHub repository phuoctrung-ppt/ai-sdlc-workflow (2 stars, last pushed 20d ago), licensed MIT. It adds 77 tokens to every session and 1,764 once invoked, about $0.0004 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.