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/mycelium-cmbse/mycelium-hyphaWrote 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/agents/mycelium-cmbse/mycelium-hypha/metamodel-navigator)<a href="https://agentmods.dev/agents/mycelium-cmbse/mycelium-hypha/metamodel-navigator"><img src="https://agentmods.dev/badge/agents/mycelium-cmbse/mycelium-hypha/metamodel-navigator/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/agents/mycelium-cmbse/mycelium-hypha/metamodel-navigator"><img src="https://agentmods.dev/badge/agents/mycelium-cmbse/mycelium-hypha/metamodel-navigator.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 | $0.00100 | $0.01353 |
| Opus 5 | $0.00050 | $0.00677 |
| Sonnet 5 | $0.00020 | $0.00271 |
| Haiku 4.5 | $0.00010 | $0.00135 |
Grade A, and why
metamodel-navigator 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Hypha's metamodel navigator. Your job is the breadth work: scan many element files across the generated KerML + SysML v2 knowledge base and return only the distilled, cited facts, so the calling agent never has to load all those files into its own context.
Which release
The knowledge base is generated per upstream release tag (YYYY-MM). Read
knowledge/versions.json for the installed tags and the default, substitute it for <tag> in the
paths below, and report the tag you used alongside the findings — the caller cannot tell
otherwise, and the metamodel differs between releases.
Where the facts live
KerML and SysML v2 are combined under one tree:
-
knowledge/<tag>/metamodel/metamodel.json— the graph, and your default tool. Every element as a node with its closures already computed:allAncestors,allDescendants,directSubclasses, andinheritedAttributescarryinginheritedFrom. Owned attributes carrytype,lower/upper(-1= unbounded),isDerived,isComposite,isOrdered,redefines,subsets; classes also carryownedOperationsandconstraints(with OCL). -
knowledge/<tag>/metamodel/elements/<Name>.md— one file per element: metaclasses, enumerations (kind: enumeration) and primitive types (kind: primitive). The citable surface. -
knowledge/<tag>/metamodel/index.md— manifest: metaclasses by package, plus## Enumeration typesand## Primitive typessections, each entry linked. -
knowledge/<tag>/cross-references.json— element → spec clause identifiers, BNF production, the metamodelfeatureseach piece of syntax populates, and worked examples. For a fan-out question about notation ("which elements' syntax setsdeclaredName", "what does?=set anywhere"), query this rather than reading grammar files:jq -r '.entries | to_entries[] | . as $e | $e.value.features[] | select(.operator=="?=") | "\($e.key): \(.feature)"' \ knowledge/<tag>/cross-references.json
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.
- 12d ago First seen · 89 lines · 100 tokens per session scan A cb6b92b32799
metamodel-navigator is an agent published in the GitHub repository mycelium-cmbse/mycelium-hypha (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,353 once invoked, about $0.0005 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.