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 stefanrossmeier/ai-craftkit --skill glossarygit clone --depth 1 https://github.com/stefanrossmeier/ai-craftkitWrote 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/stefanrossmeier/ai-craftkit/glossary)<a href="https://agentmods.dev/skills/stefanrossmeier/ai-craftkit/glossary"><img src="https://agentmods.dev/badge/skills/stefanrossmeier/ai-craftkit/glossary.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 | $0.00051 | $0.05646 |
| Opus 5 | $0.00026 | $0.02823 |
| Sonnet 5 | $0.00010 | $0.01129 |
| Haiku 4.5 | $0.00005 | $0.00565 |
Grade A, and why
glossary 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 7d 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 — 1,067 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Glossary Skill
Command: /glossary
Identify the repository's domain-specific language and create an evidence-based glossary from a Domain-Driven Design perspective.
The skill focuses on the language of the problem domain: business concepts, actors, rules, events, states, processes, classifications, measures, and artifacts. It deliberately excludes ordinary software-engineering vocabulary unless a technical-looking term has a specific meaning in the domain.
Invocation Model
Use this skill when the user calls:
/glossary
This is a skill invocation, not a shell command.
It has no command-line flags, parameters, modes, or options. If the user adds text after the invocation, treat it as plain-language scoping guidance.
Examples:
/glossary
/glossary focus on the claims workflow
/glossary inspect only the reserving and settlement areas
/glossary refresh the existing glossary and highlight terminology drift
Do not document or advertise flag-based usage.
Purpose
Generate or update:
docs/GLOSSARY.md
The document should help developers, architects, analysts, testers, product experts, and future agents use the repository's domain language consistently.
The skill should:
- identify terms that carry domain meaning
- explain those terms in plain business language
- connect definitions to repository evidence
- group terms by candidate bounded context when useful
- expose inconsistent, ambiguous, overloaded, or competing terminology
- distinguish observed language from domain-expert-approved language
- identify important domain concepts whose meaning cannot be recovered from the repository
- avoid filling the glossary with frameworks, infrastructure, and implementation jargon
A repository can reveal language that is encoded in software. It cannot, by itself, prove that this language is accepted by domain experts or used consistently in real conversations.
Therefore, treat the result as an observed or candidate ubiquitous language until a knowledgeable human reviews it.
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.
- 7d ago First seen · 1,067 lines · 51 tokens per session scan A cf7ab70e4238
glossary is a skill published in the GitHub repository stefanrossmeier/ai-craftkit (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 51 tokens to every session and 5,646 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 skills, from other repositories
solid-principles
SOLID principles checklist with Java examples. Use when a class has too many responsibilities, an abstraction leaks, or a dependency points the wrong way, and when the user asks about Single Responsibility, Open/Closed, Liskov, Interface Segregation or Dependency Inversion. For naming, duplication and method length…
security-audit
Java security checklist covering OWASP Top 10, input validation, injection prevention, and secure coding. Works with Spring, Quarkus, Jakarta EE, and plain Java. Use when reviewing code security, before releases, or when user asks about vulnerabilities.
issue-triage
Triage and categorize GitHub issues with priority labels. Use when user says "triage issues", "check issues", "review open issues", or during regular maintenance of GitHub issue backlog.
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
openlore-analyze-codebase
Run a full static OpenLore analysis and summarize architecture, call graph, refactoring issues, and duplicate code. Use when asked to analyze, map, or assess a codebase without LLM inference.
diagrams
Mermaid diagrams following the C4 model: context, container, component, sequence, ER and deployment. Use when saying "diagram", "visualize", or "architecture diagram".