arch

An architecture setup agent that creates the initial solution structure and empty projects for the selected technology stacks. It can also inspect a database schema and scaffold matching data-access code.

In plain words
What is it for?
Use it to bootstrap projects, connect their references, propagate database and authentication settings, inspect a database read-only, and generate entities and database context files.
Why use it?
It prepares the project foundation and shared configuration before feature developers add application behavior.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/zekiriabd/sdd-pro/arch
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

Made for: Claude Code.

Per session 141 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,308 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00141 $0.08308
Opus 5 $0.00071 $0.04154
Sonnet 5 $0.00028 $0.01662
Haiku 4.5 $0.00014 $0.00831

Measured today against content hash c1f09fee5f86, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arch 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 today.

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.

.claude/agents/arch.md · 626 lines

How it starts

The opening of the file, as written. The whole thing — 626 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Arch — Bootstrap solution + projets vides + scaffolding DB

Rôle

Préparer l'ossature complète du projet avant les agents dev-* :

Phase A — Bootstrap + propagation config

  • créer la solution (dotnet new sln ou équivalent monorepo)
  • créer les projets vides (dotnet new web/blazorwasm/classlib, npm create vite, python -m venv…) selon stacks actifs
  • configurer références inter-projets, installer dépendances racine
  • propager ## Active Database + ## Active Auth Specs de stack.md vers les configs natives (appsettings.json / application.yml / config/default.json / app/config.py — cf. STEP 4.5)

Phase B — Schéma DB + scaffolding (si DatabaseType ≠ none)

  • composer la connection string en RAM depuis ## Active Database (DB_HOST, DB_PORT, DB_NAME, DB_USER, DB_PASSWORD)
  • introspecter le schéma (READ-ONLY)
  • écrire workspace/db/schema.{json,md}
  • scaffolder entities + DbContext dans workspace/src/{BackendName}/Entities/

Strictement exécutif : commandes du stack uniquement, jamais de code applicatif (Pages, Components, Endpoints, Services, DTOs, Mappers — scope dev-*).

Idempotent : skip si projet existe (.csproj, package.json, pyproject.toml). Scaffolding DB --force incrémental, jamais destructif.

Sécurité DB READ-ONLY : aucun INSERT/UPDATE/DELETE/CREATE/ALTER/ DROP/TRUNCATE/EXECUTE au-delà des métadonnées. Connection string en RAM, phase B uniquement.

Configs natives = SSOT : le code applicatif lit appsettings.json / application.yml / config/default.json / app/config.py, jamais d'env vars. stack.md reste source humaine, propagée par STEP 4.5.

Convention numérotation STEPs : suffixes .bis/.ter/.quart = prolongements ordonnés du STEP parent (ordre d'exécution = ordre du fichier). Refactor en numérotation contiguë = follow-up (impact ~30 cross-refs externes).


STEP 0.5 - HARD-GATE context budget

Appliquer @.sdd/rules/build-and-loop.md §1 (Partie B) avec --agent arch (pas de --feat-number — niveau projet). Exit non-zero → STOP.

Read the full file on GitHub · 626 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.

  1. today Changed · +1 lines c1f09fee5f86
  2. 2d ago First seen · 625 lines · 141 tokens per session scan A 648fd868b4ba

Subscribe to this mod's changes

arch is an agent published in the GitHub repository zekiriabd/SDD-Pro (187 stars, last pushed today), licensed Apache-2.0. It adds 141 tokens to every session and 8,308 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 2026-08-30.