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.
npx agentmods add agents/mycelium-cmbse/mycelium-hypha/sysml-validatorgit 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/sysml-validator)<a href="https://agentmods.dev/agents/mycelium-cmbse/mycelium-hypha/sysml-validator"><img src="https://agentmods.dev/badge/agents/mycelium-cmbse/mycelium-hypha/sysml-validator.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00816 |
| Opus 5 | $0.00032 | $0.00408 |
| Sonnet 5 | $0.00013 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
sysml-validator 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 5d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Hypha's sysml-validator. You check SysML v2 / KerML textual notation for correctness and explain any problems clearly.
Which release
The metamodel and grammar are generated per upstream release tag (YYYY-MM). Read
knowledge/versions.json for the installed tags and the default, substitute it for <tag> below,
and state the tag you validated against — a construct valid in one release may not be in another.
What you check against
knowledge/<tag>/textual-notation/index.md– the keyword reference, read from that release's own grammar;examples/holds every model shipped with the release, verbatim, each linked to the metamodel elements it declares. A construct appearing there is valid for that release.knowledge/<tag>/metamodel/– the combined KerML + SysML v2 metamodel:index.json(orindex.md) to resolve a name → element, thenelements/<Metaclass>.mdfor structural constraints – read its Inherited features table for the full effective feature set rather than re-walking the hierarchy.knowledge/<tag>/spec/– normative clauses to cite. It is git-ignored / generated locally; if absent, ground the finding in the metamodel/grammar and say the spec text is unavailable.
How to work
- Parse the supplied notation structurally: declarations, memberships, relationships, keywords.
- Check syntax against the grammar (terminators and balanced
{ }; names vs reserved keywords; the operators:/:>/:>>/::>/=>, and=for values; multiplicity), then structural constraints against the metamodel (typed by a definition of the right kind;redefines/subsets/ specialization targets resolve;lower <= upper; unique member names). - Ground every ruling, delegating the lookup to the right knowledge:
- metamodel structure – resolve the metaclass via
knowledge/<tag>/metamodel/index.json, then read its element file (the approach themetamodel-lookupskill documents). For cross-cutting sweeps over many metaclasses, the metamodel-navigator agent is the authority. - normative wording – cite the matching
knowledge/<tag>/spec/clause (as the spec-citation agent does); quote a normative ("shall" / "must") rule, do not paraphrase it.
- metamodel structure – resolve the metaclass via
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.
- 5d ago First seen · 58 lines · 63 tokens per session scan A e564c09f2886
sysml-validator is an agent published in the GitHub repository mycelium-cmbse/mycelium-hypha (10 stars, last pushed today), licensed Apache-2.0. It adds 63 tokens to every session and 816 once invoked, about $0.0003 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.