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 skills add mycelium-cmbse/mycelium-hypha --skill spec-citationgit 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/skills/mycelium-cmbse/mycelium-hypha/spec-citation)<a href="https://agentmods.dev/skills/mycelium-cmbse/mycelium-hypha/spec-citation"><img src="https://agentmods.dev/badge/skills/mycelium-cmbse/mycelium-hypha/spec-citation/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/skills/mycelium-cmbse/mycelium-hypha/spec-citation"><img src="https://agentmods.dev/badge/skills/mycelium-cmbse/mycelium-hypha/spec-citation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.01367 |
| Opus 5 | $0.00039 | $0.00683 |
| Sonnet 5 | $0.00015 | $0.00273 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade A, and why
spec-citation 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 3d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec citation
Back claims with the literal text of the OMG KerML and SysML v2 specifications, always with a clause reference. Never paraphrase a normative ("shall"/"must") statement.
Releases
Clause text is generated per upstream release tag (YYYY-MM). Read knowledge/versions.json
for the installed tags and the default one, then substitute it for <tag> below. Quote from the
default release unless the user names another, and state which release the citation is from —
clause numbering shifts between releases, so a bare clause reference can be wrong for another one.
Knowledge base
knowledge/<tag>/spec/kerml/— KerML 1.0, one markdown file per clause.knowledge/<tag>/spec/sysml2/— SysML v2.0, one markdown file per clause.
Each tree has an index.md (a human-readable table of every clause → title → pages → file) and an
index.json (the same catalog, machine-readable, with entries keyed by clause number →
{title, pages, normative, file}) — use either as the entry point. index.json is handy for exact
lookup ("clause 7.4.2") or filtering (e.g. normative clauses) before reading a file; it carries
metadata only, never clause text. Clause files are named by zero-padded clause number + slug, e.g.
07.04.02-concrete-syntax.md, so a clause number sorts and greps directly.
knowledge/<tag>/spec/is generated locally bytools/spec-extractfrom your own copies of the OMG PDFs and is not shipped with the plugin (OMG licensing forbids redistributing the spec text).hypha generatefetches and cachesuvto run that extraction automatically once the PDFs are present (hypha fetchgets them by default) — no maintainer source checkout needed any more.
knowledge/<tag>/cross-references.json— committed, and available even when the clause text is not. It maps each metamodel element to the clause identifiers that treat it. It holds clause numbers only, never wording, which is exactly why it can ship.
When the clause text is missing
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.
- 3d ago Changed · +2 lines 1601d660aaf3
- 11d ago First seen · 97 lines · 77 tokens per session scan A d220e4d2f04a
spec-citation is a skill published in the GitHub repository mycelium-cmbse/mycelium-hypha (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,367 once invoked, about $0.0004 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 skills, from other repositories
reqvire-ontology-authoring
Expert workflow for creating, extending, and validating Reqvire structural ontology elements for IT engineering, systems engineering, MBSE, and system-of-interest modeling. Use for competency-question-driven OWL/Turtle vocabulary, semantic-contract boundaries, ontology hierarchy, domain/range/property modeling…
reqvire-ontology-authoring
Expert workflow for creating, extending, and validating Reqvire structural ontology elements for IT engineering, systems engineering, MBSE, and system-of-interest modeling. Use for competency-question-driven OWL/Turtle vocabulary, semantic-contract boundaries, ontology hierarchy, domain/range/property modeling…
reqvire-concept-authoring
Expert workflow for authoring Reqvire native concept schemes and concepts as SKOS thesauri. Use when creating or revising concept-scheme or concept elements, designing controlled vocabularies, concept taxonomies, broader/narrower/related links, labels, definitions, scope notes, examples, mappings, concept scheme…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.