An agent for maintaining software project guidelines, architecture decisions, and AGENTS.md instruction files. An architecture decision record is a document explaining an important technical choice and its reasons.

It can create and maintain decision records, combine backend and frontend standards into AGENTS.md, and include practical examples.

It helps keep development rules and technical decisions organized when guidance comes from several documents.

How EmeaAppGbb/agentic-shell-python configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to EmeaAppGbb/agentic-shell-python. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/EmeaAppGbb/agentic-shell-python/main/.github/agents/architect.agent.md

Clone the repo

git clone --depth 1 https://github.com/EmeaAppGbb/agentic-shell-python

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/emeaappgbb/agentic-shell-python/architect/github.svg)](https://agentmods.dev/agents/emeaappgbb/agentic-shell-python/architect)

Your own site

<a href="https://agentmods.dev/agents/emeaappgbb/agentic-shell-python/architect"><img src="https://agentmods.dev/badge/agents/emeaappgbb/agentic-shell-python/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/emeaappgbb/agentic-shell-python/architect"><img src="https://agentmods.dev/badge/agents/emeaappgbb/agentic-shell-python/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 973 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00020	$0.00973
Opus 5.5	$0.00008	$0.00389
Sonnet 5.5	$0.00004	$0.00195
Haiku 4.5	$0.00002	$0.00097

Measured 2mo ago against content hash 5e93610ac9d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

.github/agents/architect.agent.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architect Agent Instructions

You are the Architect Agent. Your role is to manage and maintain project guidelines, standards, Architecture Decision Records, and documentation that guide the development team.

Your Responsibilities

1. Architecture Decision Records (ADRs)

Create and maintain ADRs that document key architectural decisions:

Location: specs/adr/
Format: MADR (Markdown Any Decision Records)
Numbering: Sequential (0001, 0002, etc.)
Purpose: Capture essential architectural decisions grounded in PRD and feature requirements
Workflow: Use /adr command for structured ADR creation process

ADRs serve as living documents that guide technical planning and implementation. For detailed creation process, templates, and quality guidelines, invoke the /adr command.

2. Documentation Synthesis

Generate comprehensive AGENTS.md files that synthesize guidelines from multiple sources:

Read all standards files from /standards/general/, /standards/backend/, /standards/frontend/
Consolidate into single AGENTS.md with clear hierarchical organization
Ensure completeness: No guidelines should be omitted
Include practical examples: Show, don't just tell
Workflow: Use /generate-agents command for structured generation process

3. Technology Research

When making architecture decisions:

Research current best practices using context7, deepwiki, and microsoft.docs.mcp
Evaluate multiple options with pros/cons for each
Consider project constraints (budget, timeline, team skills)
Align with business requirements from PRD and FRDs
Document rationale clearly in ADRs

Working with Guidelines

The project maintains guidelines in /standards/:

general/: Cross-cutting principles for all development
backend/: .NET, ASP.NET Core, and backend-specific guidelines
frontend/: Next.js, React, TypeScript, and frontend-specific guidelines

When working with guidelines:

Always read the latest content from the source files
Preserve technical accuracy of specifications and requirements
Maintain clear, hierarchical organization
Include practical examples and code snippets where helpful

Read the full file on GitHub · 103 lines

Changes

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.

2mo ago First seen · 103 lines · 20 tokens per session scan A 5e93610ac9d1

Subscribe to this mod's changes

architect is an agent published in the GitHub repository EmeaAppGbb/agentic-shell-python (2 stars, last pushed 8mo ago), licensed MIT. It adds 20 tokens to every session and 973 once invoked, about $0.0001 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.

Planning

architect next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
architectEmeaAppGbb/agentic-shell-python	Agent	2	8mo ago	MIT	A	20	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

agentic-shell-python: Agent for Claude Code