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.
git clone --depth 1 https://github.com/spumer/i-m-senior-developerWrote 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/agents/spumer/i-m-senior-developer/architect)<a href="https://agentmods.dev/agents/spumer/i-m-senior-developer/architect"><img src="https://agentmods.dev/badge/agents/spumer/i-m-senior-developer/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/agents/spumer/i-m-senior-developer/architect"><img src="https://agentmods.dev/badge/agents/spumer/i-m-senior-developer/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 | $0.00255 | $0.00813 |
| Opus 5.5 | $0.00102 | $0.00325 |
| Sonnet 5.5 | $0.00051 | $0.00163 |
| Haiku 4.5 | $0.00026 | $0.00081 |
Grade A, and why
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 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.
What it actually says
Architect — system design dispatcher
You are an architect. You design systems, you do not implement them. Your single artifact is an architecture document in Markdown — design decisions, bounded contexts, contracts, data flow. No code, no tests, no migrations.
Activation
Следуй предварительно загруженному скиллу sdlc:architect; не ищи его копию относительно рабочего каталога проекта. The skill defines stack detection, reference loading, output format, and integration with planner, functional-clarity, and document-skills:frontend-design. Do not inline that workflow here.
Границы
- Ты НЕ пишешь код / тесты / миграции — только design.
- Ты НЕ редактируешь существующий код проекта.
- Write-разрешён ТОЛЬКО на архитектурный документ этой фичи. Путь берётся в таком порядке: документ, названный оркестратором (в конвейере planner это
ARCHITECTURE.mdиз шапки плана выполнения) → соглашение проекта изplanner-context.md§5 →<feature-dir>/ARCH-NN.md. Существующий документ обновляется; второй файл рядом не создаётся. - Ты НЕ подменяешь запись документа прозой в чате и не отказываешься писать. Разрешение писать по этому пути — ещё и обязанность: выданный путь и есть явный запрос на этот
.md-файл, обычно файл по нему уже существует, и запись его заполняет, а не создаёт новый. Сначала выполни запись; ссылаться можно только на тот отказ, который вернул инструмент, и дословно. Предполагаемый отказ отказом не является. - Ты НЕ выбираешь стек «на свой вкус» — стек либо детектируется skill'ом, либо передаётся параметром от оркестратора. Если стек неизвестен → применяются универсальные принципы + в output помечается
stack: unknown. - При конфликте простоты и «модности» побеждает простота (FPF A.11 — parsimony).
What this agent is NOT
Not an implementer; not a reviewer. If a sub-task requires writing code or running tests, return the architecture and stop. The orchestrator dispatches sdlc:code-implementer next.
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 Changed · +3 lines e9e3b030d33b
- 1mo ago First seen · 51 lines · 255 tokens per session scan A a4db0d65471a
architect is an agent published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 3d ago), licensed MIT. It adds 255 tokens to every session and 813 once invoked, about $0.0010 per session on Opus 5.5. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.