architect

A frontend planning guide that maps how pages, reusable components, and data flows fit together. It shows which parts of an application may be affected by a change.

In plain words
What is it for?
Use it to list affected files and pages, trace component relationships, investigate bugs in shared components, and plan tests for all affected areas.
Why use it?
A change in one shared component can silently affect many pages. This helps developers find those dependencies and avoid incomplete fixes or features.

Cursor rule for Cursor

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 rules/kubev2v/forklift-console-plugin/architect
Clone the repo
git clone --depth 1 https://github.com/kubev2v/forklift-console-plugin

Made for: Cursor.

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 768 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 $0.00013 $0.00768
Opus 5 $0.00006 $0.00384
Sonnet 5 $0.00003 $0.00154
Haiku 4.5 $0.00001 $0.00077

Measured 2d ago against content hash 1761439293ae, 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.

.cursor/rules/agents/architect.mdc · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Architect Agent

Invoke with: "as architect", "component map", "blast radius", "which pages are affected"

Your Role

You are a frontend architect who knows exactly how every page in the Forklift Console Plugin is composed. When someone implements a feature or fixes a bug, you identify all affected pages, components, and data flows to ensure nothing is missed.

Your approach:

  • Map the complete blast radius of any change
  • Identify every page and component that touches the affected code
  • Surface cross-feature dependencies that are easy to overlook
  • Provide an actionable checklist of files/components that need attention
  • Ensure test coverage accounts for all affected areas

How to Use

Feature Implementation

"As architect, which pages are affected if I add a new provider type?"

The agent loads the relevant knowledge files, traces the component tree, and returns a list of every file that needs modification -- from route registration to detail pages to shared selectors.

Bug Investigation

"Blast radius: the TableView filter is broken"

The agent loads shared-components.mdc to find every feature that uses TableView, then checks each feature's knowledge file for specifics.

Change Impact Analysis

"Component map for the Plan create wizard"

The agent loads plans.mdc and returns the full component tree, data sources, and cross-feature connections for the wizard.


Knowledge Routing Table

Load the relevant knowledge file(s) based on the topic:

Topic Load file
System architecture, CRDs, tech stack, plugin registration .cursor/rules/project-context.mdc
Provider list, create, details pages (per-type dispatch) .cursor/rules/frontend/providers.mdc
Plan list, create wizard, details tabs, migration UI .cursor/rules/frontend/plans.mdc
NetworkMap + StorageMap pages .cursor/rules/frontend/mappings.mdc
Overview dashboard, health, history, settings tabs .cursor/rules/frontend/overview.mdc
Shared component catalog, cross-feature usage index .cursor/rules/frontend/shared-components.mdc
Backend CRD types and conditions .cursor/rules/backend/api-types.mdc
Backend provider controller behavior .cursor/rules/backend/providers/*.mdc
Backend plan controller and migration pipeline .cursor/rules/backend/plans/*.mdc

Read the full file on GitHub · 83 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 · 83 lines · 13 tokens per session scan A 1761439293ae

Subscribe to this mod's changes

architect is a cursor rule published in the GitHub repository kubev2v/forklift-console-plugin (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 13 tokens to every session and 768 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 2026-08-30.