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 andrewcigan/vibe-dev-plugin --skill detail-architecturegit clone --depth 1 https://github.com/andrewcigan/vibe-dev-pluginWrote 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/andrewcigan/vibe-dev-plugin/detail-architecture)<a href="https://agentmods.dev/skills/andrewcigan/vibe-dev-plugin/detail-architecture"><img src="https://agentmods.dev/badge/skills/andrewcigan/vibe-dev-plugin/detail-architecture/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/andrewcigan/vibe-dev-plugin/detail-architecture"><img src="https://agentmods.dev/badge/skills/andrewcigan/vibe-dev-plugin/detail-architecture.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 | $0.00071 | $0.00315 |
| Opus 5 | $0.00036 | $0.00158 |
| Sonnet 5 | $0.00014 | $0.00063 |
| Haiku 4.5 | $0.00007 | $0.00032 |
Grade A, and why
detail-architecture 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 9d 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.
What it actually says
/detail-architecture
Детализация архитектуры через 2 агента.
Что происходит
-
Subagent
architect(Opus) расширяет V0:- API endpoint contracts (paths, methods, request/response schemas)
- Data models (схемы БД)
- Обработка ошибок (где и как)
- Каждая абстракция обоснована ≥3 случаями
-
Subagent
reordering-agent(Sonnet) строит DAG зависимостей:- Topological sort секций
- Waves для параллельной разработки
- Critical path
Output
docs/architecture-detail.mddocs/phases.md(waves + DAG)
Stage verifier
- Все компоненты детализированы
- API контракты
- Модели данных
- Каждая абстракция обоснована
Дальше
/design-handoff (если UI) или /dev-plan (если нет UI).
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.
- 9d ago First seen · 39 lines · 71 tokens per session scan A 97840ec3f333
detail-architecture is a skill published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 315 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 2026-08-31.
Other skills, from other repositories
harness
A meta-skill for designing and maintaining a project harness: a coordinated set of specialist agents, skills, and project instructions. It defines their roles, connects them to the project, and updates the setup as the work changes.
release
Release a new version of the mumei repository. Invoke when the user gives an explicit release instruction ("release it", "/release", "patch release", "ship 0.2.0"). Takes no argument or "patch" / "minor" / "major" for a SemVer bump, or a direct version such as "0.2.0". Wraps any uncommitted changes into a single…
dhpk-deploy-list
A command-line tool that builds a list of files to include in a software deployment from Git history. A deployment is the process of shipping a change to a running environment.
dhpk-php-modern-pro
PHP 7.4–8.x idiom and dual-version library-packaging guidance. Use for public APIs, version-conditional shims, supported floors, or composer constraints. Not for routine business logic. Output: a compatibility decision and verification gates.
change-verdict
Read-only verdicts for code changes, pull requests, security, tests, documents, or change risk. Use when judging an existing change or evidence set. Not for implementing fixes, generating tests, editing documents, clearing gates, or architecture-only design. Output: evidence-backed findings, degradation state, and…
dhpk-agent-architecture-audit
Full-stack diagnostic for agent and LLM applications — audits the 12-layer agent stack for wrapper regression, memory pollution, tool-discipline failures, hidden repair loops, and rendering corruption. Use when: shipping an agent/LLM feature, an agent degrades after adding wrapper/memory/tool layers, the same model…