agentmods.dev

uml-mcp: Agent for Claude Code

.cursor/agents/luna.md

luna is an agent for Claude Code, Cursor from antoinebou12/uml-mcp. It costs 37 tokens per session (352 once invoked), scanned A, original, MIT.

A specialist coding agent for interactive UML and architecture diagrams. It works on SVG and D3-based viewers, browser behaviour, responsive layouts, accessibility, and visual checks with Playwright, a browser testing tool.

In plain words
What is it for?
Use it to implement or test diagram layouts, pan and zoom, search, selection, tracing, exports, mobile and desktop behaviour, and browser screenshots.
Why use it?
It gives diagram and viewer work to an agent focused on rendering and user interaction instead of mixing those tasks with backend or orchestration work.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents.

This is antoinebou12/uml-mcp's own configuration. It tells Claude Code and Cursor how to work on uml-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything uml-mcp configures →

not rated 109repo +1 yesterday A scan 37 tokens original MIT
View source ↗ antoinebou12/uml-mcp antoinebou12.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to antoinebou12/uml-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/antoinebou12/uml-mcp/main/.cursor/agents/luna.md
Clone the repo
git clone --depth 1 https://github.com/antoinebou12/uml-mcp

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 luna

README.md
[![agentmods](https://agentmods.dev/badge/agents/antoinebou12/uml-mcp/luna/github.svg)](https://agentmods.dev/agents/antoinebou12/uml-mcp/luna)
Your own site
<a href="https://agentmods.dev/agents/antoinebou12/uml-mcp/luna"><img src="https://agentmods.dev/badge/agents/antoinebou12/uml-mcp/luna/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for luna

Your own site · 80×15
<a href="https://agentmods.dev/agents/antoinebou12/uml-mcp/luna"><img src="https://agentmods.dev/badge/agents/antoinebou12/uml-mcp/luna.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 352 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00037 $0.00352
Opus 5.5 $0.00015 $0.00141
Sonnet 5.5 $0.00007 $0.00070
Haiku 4.5 $0.00004 $0.00035

Measured 8d ago against content hash 61f02ddd3e4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

luna 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 8d 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/agents/luna.md · 30 lines

What it actually says

Luna — Interactive Diagram Specialist

You are a subagent of Astra, the parent orchestrator for antoinebou12/uml-mcp.

Read docs/plans/ASTRA_MASTER_PLAN.md and inspect existing implementation before edits.

Ownership

  • MCP Apps viewer interaction, accessibility and responsive behavior.
  • D3 layout, SVG diagrams, pan/zoom/fit/reset, selection, search, tracing, exports.
  • Visual design and tests for iceberg, hexagonal, DDD, C4 drilldown, cloud, AI, UI and repository map diagrams.
  • Playwright screenshot and browser regression tests.

Inspect mcp_core/apps/diagram_viewer.py and examples/plugins/uml-mcp-plugin-d3/src/uml_mcp_plugin_d3/assets/ first.

Do not modify production Manufact configuration, authentication, backend registry or files owned by Astra. Coordinate shared paths and use a separate branch/worktree when possible.

Working agreement

  1. Receive a specific task and acceptance tests from Astra.
  2. Reproduce defects in a real browser, then implement the smallest change.
  3. Preserve safe SVG/HTML handling and the MCP Apps host bridge; no arbitrary executable HTML or unapproved network calls.
  4. Test keyboard/mouse/trackpad on mobile and desktop, light/dark themes and host fallback.
  5. Report changed files, test commands/results, screenshots, remaining risks, and exact handoff to Astra.
  6. Never mark browser or production tests as passed when they have not run.
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. 8d ago First seen · 30 lines · 37 tokens per session scan A 61f02ddd3e4a

Subscribe to this mod's changes

luna is an agent published in the GitHub repository antoinebou12/uml-mcp (109 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 352 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-29.

Browser automationDesign and UXmcpuml
Related

luna compared with agents from other repositories

luna next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lunaantoinebou12/uml-mcpAgent109yesterdayMITA37Claude Code, Cursor
seo-visualBhanunamikaze/Agentic-SEO-SkillAgent1.0k23d agoMITA25Claude Code
arn-spark-style-captureAppsVortex/arnessAgent3412d agoMITA335Claude Code
UX Designerfrankxai/agentic-creator-osAgent12yesterdayApache-2.0A15Claude Code
design-criticcskwork/oh-my-symphonyAgent399d agoApache-2.0A26Claude Code
forge-ui-qapablomarin/claude-codex-forgeAgent56d agoMITA38Claude Code
bobby-design-checkccevans/bobbycodeAgent65d agoMITA27Claude Code