agentleFS
Sign inStart free
nodealchemynodealchemy/powernode-platform/frontend/CLAUDE.md

powernode-platform / frontend

CLAUDE.md4 starsChanged 18 days agoMITView on GitHub

React TypeScript frontend for Powernode. Query MCP before non-trivial frontend changes (full protocol: conventions/mcp-first-workflow.md). Before writing code for a non-trivial change: 1. platform.query_learnings — check for existing patterns/gotchas in the area being modified 2. platform.search_knowledge — find relevant procedures/references for the component/feature 3. platform.search_knowledge_graph — understand component relationships and page hierarchy Query MCP first. Use these files when MCP returns no relevant results:

The file

We split this CLAUDE.md into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before writing code for a non-trivial change:

    line 21
  2. Very specific:

    Use platform.discover_skills with your task description first.

    line 80

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Frontend CLAUDE.md

React TypeScript frontend for Powernode.

Critical Rules

  • currentUser?.permissions?.includes('name') - NEVER check roles
  • Theme classes only: bg-theme-*, text-theme-* - no hardcoded colors
  • Flat navigation - no submenus
  • Actions ALL in PageContainer - none in page content
  • Global notifications only - no local success/error
  • Imports: @/shared/, @/features/ for cross-feature
  • No console.log in production, no any types

MCP-First Frontend Workflow

Query MCP before non-trivial frontend changes (full protocol: conventions/mcp-first-workflow.md).

Starting a change

Before writing code for a non-trivial change:

  1. platform.query_learnings — check for existing patterns/gotchas in the area being modified
  2. platform.search_knowledge — find relevant procedures/references for the component/feature
  3. platform.search_knowledge_graph — understand component relationships and page hierarchy

Before Creating/Modifying

TaskMCP Query
New component or pageplatform.discover_skills + platform.search_knowledge query: "React component patterns"
Theme/styling changesplatform.search_knowledge query: "theme system"
Permission checksplatform.search_knowledge query: "permission system frontend"
State managementplatform.query_learnings query: "state management" — known patterns and anti-patterns
Form implementationplatform.search_knowledge query: "form patterns"
AI feature UIplatform.search_knowledge_graph query: "AI frontend" — entity relationships, page structure
Autonomy dashboard/panelsplatform.search_knowledge query: "autonomy dashboard"
Admin panelplatform.search_knowledge query: "admin panel"
API hooks / data fetchingplatform.query_learnings query: "React hooks" — established fetch patterns
Agent/team UIplatform.get_agent / platform.get_team — understand data shapes
KB article UIplatform.list_kb_articles / platform.get_kb_article — check content structure
Page UIplatform.list_pages / platform.get_page — check page data model
Memory visualizationplatform.memory_stats / platform.search_memory — understand memory tier data

During Work

  • Before new UI patterns: platform.query_learnings — check if pattern is established or has known issues
  • Before component architecture decisions: platform.search_knowledge_graph — understand feature-to-component relationships
  • Before adding dependencies: platform.query_learnings query: "package name" — check for known integration gotchas

After Work (MANDATORY for non-trivial changes)

Change typeContribution
New component patternplatform.create_learning category: pattern — document the approach
UI bug fixplatform.create_learning category: discovery — root cause + fix
New feature page structureplatform.extract_to_knowledge_graph — page hierarchy, component relationships
Reusable hook or utilityplatform.create_skill — codify the approach

Context-Aware Documentation (file fallback)

Query MCP first. Use these files when MCP returns no relevant results:

When working onMCP QueryFile Fallback
features/ai/*platform.search_knowledge query: "AI frontend"concepts/agents-and-autonomy.md
shared/components/*platform.search_knowledge query: "UI components"guides/frontend.md
Theme/stylingplatform.search_knowledge query: "theme system"reference/theme-system.md
Permission checksplatform.search_knowledge query: "permission frontend"concepts/permissions.md
Formsplatform.search_knowledge query: "form patterns"guides/frontend.md
State managementplatform.query_learnings query: "state management"guides/frontend.md
features/admin/*platform.search_knowledge query: "admin panel"guides/frontend.md
features/ai/autonomy/*platform.search_knowledge query: "AI autonomy frontend"concepts/agents-and-autonomy.md

MCP Tool Reference

Full tool catalog with parameters: reference/auto/mcp-tools.md. To load a tool's schema in a session, use ToolSearch (e.g. select:mcp__powernode__platform_search_knowledge).

Key Specialists

Use platform.discover_skills with your task description first. File fallback:

  • Frontend guide — React architecture, UI components, dashboards, forms, state, plugin UI, WebSocket integration

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free