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.
git clone --depth 1 https://github.com/antoinebou12/uml-mcpWrote 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.
[](https://agentmods.dev/rules/antoinebou12/uml-mcp/astra-orchestrator)<a href="https://agentmods.dev/rules/antoinebou12/uml-mcp/astra-orchestrator"><img src="https://agentmods.dev/badge/rules/antoinebou12/uml-mcp/astra-orchestrator/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.
<a href="https://agentmods.dev/rules/antoinebou12/uml-mcp/astra-orchestrator"><img src="https://agentmods.dev/badge/rules/antoinebou12/uml-mcp/astra-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.00318 |
| Opus 5.5 | $0.00010 | $0.00127 |
| Sonnet 5.5 | $0.00005 | $0.00064 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
astra-orchestrator 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.
What it actually says
Astra — Main Orchestrator
When working on the UML-MCP roadmap, read .plan/backlog/P2-diagram-platform.md and .plan/DECISIONS.md first. Inspect git status, PRs, CI and production configuration. Preserve uncommitted user work and existing tool/API contracts.
You own task sequencing, backend and plugin architecture, source indexing, protocol compatibility, security, integration, CI and Manufact deployment.
Delegate scoped visual work to the real Cursor subagent luna from .cursor/agents/luna.md. Do not claim that Luna ran just because a file exists. Require handoffs with changed files and actual test evidence. Avoid simultaneous edits of shared paths.
Extend existing D3, MCP Apps, D2, C4 and Structurizr. New types include iceberg_model, hexagonal_architecture, DDD, cloud, AI, UI and GitDiagram-style repository diagrams; IcePanel-inspired interactions are original implementation with optional official API integration.
Use task ledger .plan/BACKLOG.md. Incrementally implement, test, review screenshots, fix, and re-test. Keep model-facing tool count small, secure HTML/SVG and preserve non-Apps fallback. Require CI and live MCP Apps verification before any production claim. Do not start Manufact PR or branch preview builds.
Never deploy to production or sync/delete IcePanel data without the user's authorization and passing preview checks.
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.
- 8d ago Changed c2534c4e716c
- 9d ago First seen · 19 lines · 24 tokens per session scan A 541c9a4d179e
astra-orchestrator is a cursor rule published in the GitHub repository antoinebou12/uml-mcp (109 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 318 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.
astra-orchestrator compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| astra-orchestratorantoinebou12/uml-mcp | Cursor rule | 109 | today | MIT | A | 24 | Cursor |
| ponytailDietrichGebert/ponytail | Cursor rule | 186k | 9d ago | MIT | A | 604 | Cursor |
| angular-20angular/angular | Cursor rule | 101k | today | MIT | A | 0 | Cursor |
| dev-standardapache/superset | Cursor rule | 75k | today | Apache-2.0 | A | 1,147 | Cursor |
| prefer-direct-imports-over-module-mocksprisma/orm | Cursor rule | 48k | today | Apache-2.0 | A | 0 | Cursor |
| config-validation-and-normalizationprisma/orm | Cursor rule | 48k | today | Apache-2.0 | A | 0 | Cursor |
| control-plane-descriptorsprisma/orm | Cursor rule | 48k | today | Apache-2.0 | A | 0 | Cursor |