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 skills/reqvire-org/reqvire/reqvire-sysengnpx skills add reqvire-org/reqvire --skill reqvire-sysenggit 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-syseng)<a href="https://agentmods.dev/skills/reqvire-org/reqvire/reqvire-syseng"><img src="https://agentmods.dev/badge/skills/reqvire-org/reqvire/reqvire-syseng.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 | $0.00150 | $0.08765 |
| Opus 5 | $0.00075 | $0.04383 |
| Sonnet 5 | $0.00030 | $0.01753 |
| Haiku 4.5 | $0.00015 | $0.00877 |
Grade A, and why
reqvire-syseng scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
92% identical to reqvire-syseng — 52 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Engineering and MBSE Skill
You are an expert semantic engineering and MBSE practitioner specializing in Reqvire. You orchestrate Reqvire commands and provide guidance for ontology-driven engineering, capability modeling, requirements, contracts, verification, and AI-native engineering knowledge graphs.
Environment Setup
Use the Reqvire npm runner by default so Codex workflows do not require a separate binary install.
Default command form:
npx -y "${REQVIRE_NPX_PACKAGE:-@reqvire-org/reqvire@latest}" --workspace "$PWD" <command>
Workspace policy:
- Run commands from the intended effective workspace root, or pass that root with
--workspace. - The effective workspace root must contain at least one eligible Git worktree; otherwise there is no local SOI model-processing scope.
- Reqvire parses and reports only files and artifacts under the effective workspace root that are inside eligible Git worktrees. Non-Git workspace folders are ignored.
- Git worktree roots, branches, remotes, and commits are source-control metadata. They do not redefine Reqvire identifier roots; identifiers and paths stay workspace-root-relative.
To check:
npx -y "${REQVIRE_NPX_PACKAGE:-@reqvire-org/reqvire@latest}" --workspace "$PWD" --version
Version policy:
- Use
@reqvire-org/reqvire@latestby default for assistant workflows. - Pin by setting
REQVIRE_NPX_PACKAGE, for exampleexport REQVIRE_NPX_PACKAGE=@reqvire-org/[email protected]. - Use a locally installed
reqvirebinary only when the user explicitly needs offline or non-npm execution.
Element Types
| Category | Type | Purpose |
|---|---|---|
| Capabilities | capability |
Coherent operational, product, business, regulatory, or system ability that bridges ontology, requirements, and verification |
| Requirements | requirement |
Implementable system obligations (functional, performance, interface, compliance) |
| Ontology | ontology |
First-class OWL/Turtle vocabulary and semantic model terms reusable by capabilities and requirements |
semantic-contract |
Reusable SHACL shape profile that uses ontology and constrains requirements | |
| Concepts | concept-scheme |
Native SKOS thesaurus or concept-scheme root that owns concept_base and concept_prefix |
concept |
Native curated SKOS concept generated from Markdown body text, labels, examples, and concept relations | |
| Contracts | source |
External need, regulation, policy, or source material owned by a requirement |
specification |
Detailed definitions refining a requirement | |
constraint |
Limits and boundaries on system behavior | |
behavior |
How the system behaves in specific conditions | |
state |
Lifecycle states, state machines, transitions, and state-dependent contracts | |
input-output |
Payloads, messages, documents, schemas, fixtures, and data contracts | |
| Verification planning | verification-objective |
Verification objective or grouping node; may derive from verification-family elements but does not verify requirements/capabilities and cannot use satisfiedBy |
| Verifications | test-verification |
Automated/manual testing (evidence-backed; requires satisfiedBy) |
formal-proof-verification |
Formal proof, model checking, theorem proving, generated fixtures, or proof reports (evidence-backed; requires satisfiedBy) | |
analysis-verification |
Review, calculation, simulation | |
inspection-verification |
Visual examination, audit | |
demonstration-verification |
Showing capability works |
What ships with it
20 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.
- references/AddCapability.md 24 KB
- references/AddRequirement.md 5.5 KB
- references/AddVerification.md 8.7 KB
- references/CapabilitySemanticContractRefactor.md 14 KB
- references/Collect.md 6.4 KB
- references/ConsolidateRequirements.md 9.7 KB
- references/Containment.md 5.4 KB
- references/ContainmentStructureRefactor.md 11 KB
- references/CreatingTasks.md 16 KB
- references/DesignDocOwnership.md 2.3 KB
- references/explore.md 8.5 KB
- references/Link.md 7.4 KB
- references/Move.md 9.5 KB
- references/Remove.md 2.7 KB
- references/RenameElement.md 2.5 KB
- references/Setup.md 3.7 KB
- references/SpecificationLanguageCleanup.md 2.7 KB
- references/SpecificationsExtractionLogic.md 13 KB
- references/SubmodelRefactor.md 6.5 KB
- references/VerificationAlignment.md 1.2 KB
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 First seen · 478 lines · 150 tokens per session scan A 5e4bb2eab131
reqvire-syseng is a skill published in the GitHub repository reqvire-org/reqvire (19 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 150 tokens to every session and 8,765 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to reqvire-syseng, differing in 52 lines, and is treated as a copy.
Other skills, from other repositories
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.
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.