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/etr/groundwork/domain-modelingnpx skills add etr/groundwork --skill domain-modelinggit clone --depth 1 https://github.com/etr/groundworkWhat 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 | $0.00032 | $0.01095 |
| Opus 5 | $0.00016 | $0.00548 |
| Sonnet 5 | $0.00006 | $0.00219 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
domain-modeling 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 2d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Modeling
Overview
A project's agents are verbose and misaligned when they lack a shared language: the same concept gets three names, one name covers three concepts, and every prompt re-explains what a term means. A tight glossary fixes this — it collapses ambiguity and tokens at once.
Core principle: the glossary is terminology only. One authoritative definition per term, and nothing else. It is never a spec, never an architecture doc, never a scratchpad. The moment an entry carries implementation detail or a design decision, it stops being a glossary and starts rotting.
The glossary lives at {{specs_dir}}/glossary.md.
When to Use
- Defining a product or feature and a term keeps getting used loosely or two ways ([[design-product]], [[understanding-feature-requests]])
- Architecture work surfaces concepts the team has no agreed name for ([[design-architecture]])
- You catch yourself re-explaining the same concept across prompts or docs
Lazy Creation
{{specs_dir}}/glossary.md does not exist until the first term resolves. Do not scaffold an empty file or a placeholder. An empty glossary is sediment; create the file when you have a real first entry, not before.
Process
Capture terms inline, as they crystallize during design and requirements work — never in a batch at the end. Batching loses the context that made the term precise.
- Capture on crystallization. A concept earns an entry the moment it has a stable, agreed meaning. Write it immediately, in the format below. Do not wait for a "glossary pass."
- Challenge vague or conflicting language on the spot. When usage drifts, name it: "Your glossary defines X as A, but you're using it as B — which is it?" Resolve to one definition; update the entry or the usage, never both meanings.
- Stress-test relationships with concrete edge cases. Walk a real scenario at the boundary — empty, zero, expired, two-at-once — and check the definition and its links still hold. If the scenario breaks the entry, the term was underspecified; tighten it.
- Cross-check terms against the code. Surface contradictions where the code's structures and names disagree with the agreed term. A glossary that contradicts the codebase is worse than none — reconcile the name, the definition, or the code.
What ships with it
1 file 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.
- 2d ago First seen · 69 lines · 32 tokens per session scan A 045da7f32a37
domain-modeling is a skill published in the GitHub repository etr/groundwork (42 stars, last pushed 21d ago), licensed MIT. It adds 32 tokens to every session and 1,095 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…