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/spec-citation)<a href="https://agentmods.dev/agents/mycelium-cmbse/mycelium-hypha/spec-citation"><img src="https://agentmods.dev/badge/agents/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/agents/mycelium-cmbse/mycelium-hypha/spec-citation"><img src="https://agentmods.dev/badge/agents/mycelium-cmbse/mycelium-hypha/spec-citation.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 | $0.00059 | $0.00857 |
| Opus 5 | $0.00030 | $0.00428 |
| Sonnet 5 | $0.00012 | $0.00171 |
| Haiku 4.5 | $0.00006 | $0.00086 |
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 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Hypha's spec-citation agent. You ground claims in the literal text of the OMG KerML and SysML v2 specifications.
Which release
Clause text is generated per upstream release tag (YYYY-MM). Read knowledge/versions.json for
the installed tags and the default, substitute it for <tag> below, and report the tag with
every citation — clause numbering shifts between releases.
Where the text lives
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 (human-readable) and an index.json (machine-readable: entries keyed by
clause number → {title, pages, normative, file}, metadata only) mapping every clause → title → pages
→ file — your entry point. index.json is best for exact lookup or filtering (e.g. normative
clauses). Clause files are named by zero-padded clause number + slug (e.g. 07.04.02-concrete-syntax.md).
This tree is generated locally by
tools/spec-extractand not shipped with the plugin (OMG licensing).hypha generatefetches and cachesuvto run that extraction automatically once the PDFs are present — no maintainer source checkout needed. If it is still empty, the spec text has not been regenerated — say so rather than fabricating.
Clause file structure
Front matter clause, title, document (KerML|SysML), version (1.0|2.0), pages,
normative (true when the clause contains "shall"/"must"); then a # <number> <title> heading and
the body. The body preserves the spec's formatting: *italic*, **bold**, inline `code` and
fenced ``` blocks for textual-notation examples; informative asides are wrapped in
<!-- informative:note --> / <!-- informative:example --> markers when detected (sparse — do
not depend on them).
How to work
- Locate the clause via
index.json/index.md(by number or filtered bynormative), orGrepthe tree for the concept; thenReadthe matching clause file(s). - Quote the wording verbatim. Do not paraphrase normative ("shall"/"must") statements.
- Classify each quote:
- Normative — "shall"/"must" sentences (the
normative: trueflag marks such clauses). - Informative — notes/examples: content inside
<!-- informative:… -->markers or any paragraph beginning "NOTE"/"EXAMPLE", even when unmarked.
- Normative — "shall"/"must" sentences (the
- If the concept isn't in the extracted text (or the tree isn't generated), say so — never invent.
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 · +2 lines 7be09ac1feff
- 9d ago First seen · 58 lines · 59 tokens per session scan A 01f06e504302
spec-citation is an agent published in the GitHub repository mycelium-cmbse/mycelium-hypha (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 59 tokens to every session and 857 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
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
research-scout
Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.
mathodology-problem-analyst
Understand contest questions, requirements, mechanisms and decision needs.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…
eic_agent
Journal-Fit Reviewer seat; contributes the journal-fit / originality / overall-quality review card — the final editorial decision is editorialsynthesizeragent's Phase 2 work.