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 version-managementgit 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/version-management)<a href="https://agentmods.dev/skills/mycelium-cmbse/mycelium-hypha/version-management"><img src="https://agentmods.dev/badge/skills/mycelium-cmbse/mycelium-hypha/version-management/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/version-management"><img src="https://agentmods.dev/badge/skills/mycelium-cmbse/mycelium-hypha/version-management.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 | $0.00085 | $0.01064 |
| Opus 5 | $0.00043 | $0.00532 |
| Sonnet 5 | $0.00017 | $0.00213 |
| Haiku 4.5 | $0.00009 | $0.00106 |
Grade A, and why
version-management 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 yesterday.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version management
Hypha keeps nothing generated in git: every release's metamodel, textual notation and
cross-references is fetched and generated on this machine, on request. This skill is the
vocabulary for doing that conversationally - list, fetch, switch, remove - all through the hypha
CLI (self-contained; no toolchain needed).
Always confirm before acting
- Fetching costs real time (minutes for a first fetch) and a network round-trip. Never fetch a release just because a hook mentioned one exists - say what's available and ask.
- Removing is destructive (the release's files are deleted). Confirm which tag before running it.
- Switching the default is cheap and reversible - still worth naming what changed, not silent.
Listing what's local vs. online
hypha check
Prints installed releases (with which is default) next to what's newest online, and tells you if a
newer release exists. This is the same comparison the SessionStart hook already ran once at session
start - re-run it if the user asks "what versions do I have" later in a long conversation, since the
hook only checks once per session.
For the full upstream list rather than just the newest few, use hypha discover (--limit 0 for
everything, newest first).
Fetching a release
Run both steps in the foreground - the user sees real progress as they stream, there is nothing to poll for:
hypha fetch --tag <tag>
hypha generate --tag <tag>
fetch downloads that release's metamodel XMI, textual sources, and (by default) the OMG
specification PDFs into sources/<tag>/ - all git-ignored, all local only. generate builds
knowledge/<tag>/ from what was fetched. fetch switches the default to whatever it just fetched,
every time - if the user wants to add a release alongside what's already installed without
switching (e.g. "also get me an older one for comparison"), pass --no-default:
hypha fetch --tag <tag> --no-default
hypha generate --tag <tag>
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.
- yesterday Changed · +3 lines 3dfec2c5d845
- 9d ago First seen · 93 lines · 85 tokens per session scan A 88e15b56e3e1
version-management is a skill published in the GitHub repository mycelium-cmbse/mycelium-hypha (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 85 tokens to every session and 1,064 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.