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 znlgis/my-opencode-deepseek-config --skill domain-modelinggit clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-configWrote 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/znlgis/my-opencode-deepseek-config/domain-modeling)<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/domain-modeling"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/domain-modeling/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/skills/znlgis/my-opencode-deepseek-config/domain-modeling"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/domain-modeling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.00581 |
| Opus 5 | $0.00035 | $0.00291 |
| Sonnet 5 | $0.00014 | $0.00116 |
| Haiku 4.5 | $0.00007 | $0.00058 |
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 today.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Modeling
An active discipline for keeping a project's domain language precise. It owns
the CONTEXT.md glossary — a shared vocabulary of domain terms — and decides
when a decision warrants an ADR. Trigger it when terms are used inconsistently,
terminology drifts, or the same concept keeps being re-explained across
sessions (each re-explanation wastes tokens that a one-sentence entry replaces).
Layout
- A single
CONTEXT.mdat the project root holding the glossary, plusdocs/adr/NNNN-*.mdfor architectural decisions. - For a codebase with several distinct contexts, use
CONTEXT-MAP.mdinstead. - Create the file lazily — only when a term actually needs pinning down. Do not scaffold an empty glossary up front.
During a session
- Challenge terms. When a word is used two ways, name the ambiguity and propose the sharper meaning.
- Sharpen fuzzy language. Replace vague phrasing with the concrete term the code actually implements.
- Stress-test relationships. Ask whether the way two concepts relate in conversation matches how they relate in code.
- Cross-reference claims against code. A glossary entry that contradicts the implementation is wrong — fix the entry or the code.
- Update
CONTEXT.mdinline, as you discover the sharper meaning. Never batch glossary edits at the end of a session. - Pin repeated explanations. When the same concept needs more than two
sentences across messages or sessions, add a one-sentence
CONTEXT.mdentry so it never needs re-explaining.
CONTEXT.md rules
- It is a glossary only — terms and their precise meanings. No implementation details, no how-to, no prose essays.
- One entry per term, one sentence per meaning where possible.
- If a term is genuinely contested, mark it
Flagged:and note the competing meanings rather than silently picking one.
When to offer an ADR
Offer an architectural decision record only when all three hold:
- The decision is hard to reverse.
- It would be surprising without context.
- There was a real trade-off between viable options.
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.
- today Changed · +5 lines · +24 tokens per session 5e6ca370fabe
- 5d ago First seen · 51 lines · 46 tokens per session scan A 1d32773ba698
domain-modeling is a skill published in the GitHub repository znlgis/my-opencode-deepseek-config (57 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 581 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 2026-09-03.
Other skills, from other repositories
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
image-generator
Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.
weibo-poster
A writing guide for Weibo, a Chinese microblogging platform similar to a short-post social network. It covers concise posts, longer posts, hashtags, @ mentions, image layouts, and posting-time suggestions.
excel-helper
A spreadsheet assistant for Excel, a program used to organize, calculate, and analyze tabular data. It covers formulas, pivot tables, charts, data cleaning, and VBA macros, which are small automation programs for Excel.