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 john7ross/dochub-architect-tool --skill dochub-architectgit clone --depth 1 https://github.com/john7ross/dochub-architect-toolWrote 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/john7ross/dochub-architect-tool/dochub-architect)<a href="https://agentmods.dev/skills/john7ross/dochub-architect-tool/dochub-architect"><img src="https://agentmods.dev/badge/skills/john7ross/dochub-architect-tool/dochub-architect/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/john7ross/dochub-architect-tool/dochub-architect"><img src="https://agentmods.dev/badge/skills/john7ross/dochub-architect-tool/dochub-architect.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00136 | $0.07516 |
| Opus 5 | $0.00068 | $0.03758 |
| Sonnet 5 | $0.00027 | $0.01503 |
| Haiku 4.5 | $0.00014 | $0.00752 |
Grade A, and why
dochub-architect 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 10d 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 — 649 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DocHub — перенос схем в архитектурный репозиторий
Работа идёт в architectural-repository — это YAML для DocHub, не код сервисов.
Отвечай пользователю на русском.
Инструменты: MCP-сервер dochub (см. tools/install-mcp.md).
Справочник ошибок: reference.md · Шаблон: subdomain-template.yaml
Шаг 0. Прочитать накопленное и спросить недостающее
Первым делом — настройки и накопленные правила:
dochub_workspace()
dochub_lessons()
dochub_workspace хранит пути, которые не меняются от задачи к задаче:
арх.репозиторий и доменную схему. Если они уже заданы — не спрашивай их,
остальные инструменты подставят пути сами. Если чего-то не хватает,
инструмент скажет чего именно: спроси только это и сохрани обратно с
save=true, чтобы вопрос больше не возникал.
Там решения, подтверждённые пользователем на прошлых схемах: как принято
называть сущности, чей поддомен владеет очередями, что выносят на диаграмму.
Правила с высоким seen подтверждались не раз — им доверяй больше.
Не переспрашивай то, что уже записано. Смысл накопления в том, чтобы пользователь не объяснял одно и то же каждый раз.
Если накопленное правило противоречит тому, что видишь в текущей схеме — скажи об этом прямо и уточни, изменилось ли соглашение.
Ответ dochub_workspace показывает и режим automode. Если он включён —
работай по разделу «Автоматический режим» в конце этого шага.
Предложи готовый сценарий, если он подходит
Вместе с проектом идут сценарии для инструмента Workflow (каталог
workflows/). Пользователь про них знать не обязан — скажи сам и спроси,
запускать ли:
| Задача пользователя | Сценарий | Что даёт |
|---|---|---|
| несколько схем сразу | dochub-batch |
по агенту на схему: черновик, проверка, общий отчёт |
| «отревьюй чужой MR» | dochub-mr-review |
агент на изменённый файл, каждая находка проверяется скептиком |
Правила простые:
What ships with it
4 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.
- 10d ago First seen · 649 lines · 136 tokens per session scan A 98fa67590956
dochub-architect is a skill published in the GitHub repository john7ross/dochub-architect-tool (0 stars, last pushed 1mo ago), licensed MIT. It adds 136 tokens to every session and 7,516 once invoked, about $0.0007 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
archinsight
Create, edit, import, analyze, repair, validate, inspect, and render Archinsight Insight architecture-as-code models and custom views. Use when working with .ai models or .aiq queries, migrating architecture from another DSL or diagram, C4-style architecture models, system/container/component/code diagrams, deployment…
likec4-architecture
Build and maintain software architecture as code with LikeC4 DSL. Use when tasks mention architecture diagrams, C4/context/container/component views, system landscape, dependency/integration maps, or when the user wants architecture generated/evolved from code. Apply for creating new .c4/.likec4 models, updating…
diagram-design
Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar chart (polar/radial lollipop), loop/flywheel, nested, tree, org chart, layer stack, Venn, pyramid/funnel, treemap, bar, waterfall, line, Gantt and scatter charts…
drawio-skill
Create, edit, synchronize, inspect, test, and publish editable draw.io diagrams. Use when the user explicitly requests draw.io/diagrams.net, needs a polished architecture, ERD, UML, sequence, C4, SysML, BPMN, network, swimlane, ML, or infrastructure diagram, wants code/IaC/SQL/OpenAPI converted into a diagram, or…
pr-lens
WHAT: Draws a code change or part of a codebase as an animated architecture or data-flow diagram, on its own or in a pull request. WHEN: asked to diagram, visualise or explain a change or a system, or when a pull request should carry a diagram. KEYWORDS: PR Lens, diagram, architecture, data flow, visualise, visualize…
audit-scientific-figure
Review and score an existing scientific illustration in visible draw.io, Microsoft PowerPoint, or WPS Presentation without hiding defects through flattening. Use for reference-fidelity checks, layout cleanup, connector review, text-fit checks, deep editability and raster-atomicity inspection, local-region gates, or…