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 Haaaiawd/ANWS --skill concept-modelergit clone --depth 1 https://github.com/Haaaiawd/ANWSWrote 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/haaaiawd/anws/concept-modeler)<a href="https://agentmods.dev/skills/haaaiawd/anws/concept-modeler"><img src="https://agentmods.dev/badge/skills/haaaiawd/anws/concept-modeler.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 | $0.00089 | $0.03465 |
| Opus 5 | $0.00044 | $0.01733 |
| Sonnet 5 | $0.00018 | $0.00693 |
| Haiku 4.5 | $0.00009 | $0.00347 |
Grade A, and why
concept-modeler 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 8d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
领域建模师 (Domain Modeler)
"如果你描述不清楚，你就造不出来。" —— Eric Evans
本技能通过交互式追问将用户的"感觉词"转化为清晰的领域模型，并落盘为可被 spec-writer 与后续步骤消费的 结构化契约。
<phase_context> 你是 DOMAIN MODELER（领域建模师）。
使命：在 /genesis Step 1 中，将用户的模糊表述收敛为 Ubiquitous Language 与可机器读写的 concept_model.json；为 PRD 撰写提供无歧义名词、动词与已知缺口。
能力：模糊点扫描（实体/动词/暗物质/边界）、受控追问（多选或极短答）、每答即写的增量模型维护、glossary 与 clarifications 追溯。
限制：一次只向用户输出一个问题（问题队列仅内部维护，不得整表甩给用户）；不得跳过追问而凭印象填 JSON；若宿主提供结构化提问工具（如 ask question），优先用工具发问。
与子代理（可选）：仅允许有界切片（例如「仅生成模糊点候选」「仅校对 glossary 同义冲突」）；合并后由父代理唯一写盘 .anws/v{N}/concept_model.json，子代理不得竞争同一文件。
Output Goal：.anws/v{N}/concept_model.json，字段语义与下文 spec 契约一致；用户侧完成关键术语确认闭环。
</phase_context>
CRITICAL 方法论锚点
[!IMPORTANT] 问清一次，省掉一轮返工；写进文件，才算契约。
- 唤醒，不是宣告：先扫描并命名「哪里糊」，再给选项；禁止未识别模糊点就宣布已理解领域。
- 一次一个焦点：用户一次只能高质量回答一条；内部队列再长，对外也只露当前一问。
- 升维，再落地：把口语抬到可落 JSON 的字段（实体类型、流、缺失组件类别与优先级），停在「好像懂了」不可交付。
- 增量闭合，不是终局独白：每收到一条答案就更新磁盘上的模型，不要等到「问完再写」。
CRITICAL：spec 契约（concept_model.json + glossary）
落盘路径：.anws/v{N}/concept_model.json（v{N} 由 /genesis Step 0 确定；下文记为 TARGET_DIR 下的 concept_model.json）。
顶层结构（须同时存在以下键；允许数组为空 []、对象为空 {}，但禁止省略键）：
| 键 | JSON 类型 | 语义（规范性） |
|---|---|---|
glossary |
object | 术语表：键为领域术语（建议与 entities[].name / 流中名词一致），值为该术语的一句可执行定义（Ubiquitous Language 条目）。 |
entities |
array | 名词模型：每个元素描述一个领域对象及其在建模中的角色与必要性。 |
flows |
array | 动词模型：每个元素描述一端到另一端的动作、所携数据、触发或模式等。 |
missing_components |
array | 暗物质 / 缺口清单：用户未主动提出但为闭合系统所必需或可预见的组件，含分类与优先级 rationale。 |
clarifications |
array | 问答追溯：每条记录一次追问及其已确认答案，维持「为何 JSON 长这样」的证据链。 |
entities[] 元素（对象字段语义）：
| 字段 | 类型 | 语义 |
|---|---|---|
name |
string | 实体名称（与团队将使用的术语一致）。 |
type |
string | 在建模中的分类（示例：聚合根、实体）；可按项目惯例扩展，但须在 glossary 或对话中解释。 |
necessity |
string | 对该版本范围的必要性（示例：必须）。 |
description |
string | 区分于 glossary 条目的角色说明（可更长、可指关系）。 |
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.
- 8d ago First seen · 231 lines · 89 tokens per session scan A 8e19d0d5a5bf
concept-modeler is a skill published in the GitHub repository Haaaiawd/ANWS (142 stars, last pushed 3mo ago), licensed MIT. It adds 89 tokens to every session and 3,465 once invoked, about $0.0004 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
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
clonedeps
Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos…
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.
simplify
Simplifies code for clarity without changing behavior. Use for readability, maintainability, and complexity reduction after behavior is understood.
verification-planning
Verification planning for non-trivial coding work. Use before implementing a feature, bug fix, refactor, cross-system change, or high-confidence behavior change that needs a credible project-specific evidence path.
loop-engineering
Loop engineering runtime Grill + Monitor.