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 reqvire-org/reqvire --skill reqvire-concept-authoringgit clone --depth 1 https://github.com/reqvire-org/reqvireWrote 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/reqvire-org/reqvire/reqvire-concept-authoring)<a href="https://agentmods.dev/skills/reqvire-org/reqvire/reqvire-concept-authoring"><img src="https://agentmods.dev/badge/skills/reqvire-org/reqvire/reqvire-concept-authoring.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 5.1 | $0.00116 | $0.03048 |
| Opus 5 | $0.00058 | $0.01524 |
| Sonnet 5 | $0.00023 | $0.00610 |
| Haiku 4.5 | $0.00012 | $0.00305 |
Grade A, and why
reqvire-concept-authoring 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 6d 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.
This is a copy
100% identical to reqvire-concept-authoring — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reqvire Concept Authoring
Author curated terminology as native Reqvire Markdown elements, not as SKOS Turtle inside ontology elements. Reqvire generates skos:ConceptScheme and skos:Concept RDF from concept-scheme and concept elements.
Use this skill for thesaurus work: stakeholder terminology, controlled vocabularies, synonyms, definitions, broader/narrower taxonomy, related concepts, concept mappings, and concept references from capabilities, requirements, contracts, or verifications.
Use reqvire-ontology-authoring instead when the work is structural OWL/RDFS vocabulary, classes, properties, individuals, axioms, SHACL targets, or semantic contracts.
Use reqvire-syseng instead when the main change is to capabilities,
requirements, specifications, verification elements, evidence, coverage,
change-impact workflows, or broader model refactoring. This skill may update
concept references on those elements only as part of concept-authoring work.
Reqvire Operations for Concept Authoring
Use Reqvire as the source-of-truth runtime when authoring or changing native concept schemes and concepts.
- Work from the intended effective workspace root unless the user gives a different workspace; the workspace must contain at least one eligible Git worktree.
- Default CLI form:
npx -y "${REQVIRE_NPX_PACKAGE:-@reqvire-org/reqvire@latest}" --workspace "$PWD" <command>. - Inside the Reqvire source repository,
cargo run -- <command>is also acceptable when the local binary is the intended target. - Inspect authored concepts with
search --filter-type concept-scheme --json,search --filter-type concept --json,model --filter-type concept-scheme --json,semantic export --layer concepts,concepts export, andconcepts validate. - Use
semantic export --layer ontologies --layer conceptswhen checking authored structuralreqvire:mapsToConceptbridge triples together with generated native SKOS concepts. Usesemantic export --layer modelwhen checking downstream graph-store model facts. - Prefer Reqvire CLI mutation commands for broad structural edits when available, such as
add,link,relink,mv,mv-file,mv-folder,rm, andrename-element. - Manual Markdown edits are valid for focused authoring. Preserve
# Elements,### Element Name,#### Metadata, and Reqvire relation list syntax. - Place concept-scheme and concept elements under
system-model/Thesaurusunless the existing project uses a differentsystem-model/content structure. - Author concept-scheme elements with
type: concept-scheme,concept_base, andconcept_prefix; this element is the namespace and SKOSConceptSchemeholder. - Author concept elements with
type: concept; the main body is the SKOS definition-like human explanation. Do not add#### Details,#### Ontology,#### Shapes,#### Definition, or#### Top Conceptsto concept elements. - Use
#### Labels,#### Scope Note,#### Examples, and#### Mappingsfor SKOS-specific concept authoring fields when needed. - Use
#### Relationsfor Reqvire-authored links:derivedFromfor scheme/parent containment,broader/narrowerfor taxonomy,relatedfor associative links, andexactMatch/closeMatchfor intentional concept-to-concept mappings. - Relation syntax is
* relationName: [Target Element](path.md#target-element). - Keep ontology-to-concept bridges in ontology Turtle with
reqvire:mapsToConcept; do not model those bridges as concept Markdown fallback data. - When changing concept identity, check dependent ontology bridges, concept references, Explorer thesaurus data, MCP concept tools, and any tests that assert generated SKOS IRIs.
- When validation is part of the task, run focused checks such as
validate,semantic export --layer concepts,concepts validate, and any affected fixture tests before finishing.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 194 lines · 116 tokens per session scan A bb34ab32fb57
reqvire-concept-authoring is a skill published in the GitHub repository reqvire-org/reqvire (19 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 116 tokens to every session and 3,048 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to reqvire-concept-authoring, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
causal
Analyze cause-and-effect relationships in the Semantica knowledge graph — causal chains, interventions, counterfactuals, and causal influence scores.
arxiv
Search and retrieve academic papers from arXiv by keyword, author, category, or ID, and read abstracts or full PDFs. Free, keyless. Use when asked to "find papers on", "search arXiv", "summarize this paper", or given an arXiv ID/link.
jupyter
Run Python data-science work through Jupyter — execute notebooks headlessly, run cells against a live kernel, and convert notebooks to scripts/HTML. Keyless, local. Use when asked to "run this notebook", "execute these cells", "analyze this dataset in Python", "convert notebook to".
context-generate
Assemble a context package (code graph, requirements, constraints, blast radius) before a downstream generation task runs - human-approved, source-attributed. Do NOT use for simple lookups.
metamodel-lookup
Look up the structure of the OMG SysML v2 / KerML metamodel (not OMG UML 2.x) – a metaclass's features, supertypes, subtypes, redefinitions, multiplicities and constraints, plus enumerations and primitive types. Use when the user asks how a SysML v2 or KerML element (e.g. PartUsage, ConnectionDefinition, Feature) is…
model-library-lookup
Look up what a SysML v2 / KerML standard model library element means or where it is declared (e.g. ISQBase::mass, ScalarValues::Real, SysML.sysml's Parts::Part) – the normative library packages a user's own model specializes with :>, not the metamodel itself. Use when the user references a qualified name from ISQ…