tech-architect

A technical architecture adviser that turns product requirements into decisions about the software stack, data model, APIs, hosting, and security.

In plain words
What is it for?
Use it to plan backend, mobile, database, authentication, hosting, and messaging choices for a software project.
Why use it?
It helps choose a workable technical foundation and records why each major decision was made. It can also suggest alternatives when the preferred tools do not fit.

Agent

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/arnwaldn/project-architect/tech-architect
Clone the repo
git clone --depth 1 https://github.com/arnwaldn/project-architect
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 838 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 $0.00034 $0.00838
Opus 5 $0.00017 $0.00419
Sonnet 5 $0.00007 $0.00168
Haiku 4.5 $0.00003 $0.00084

Measured 2d ago against content hash b7982e029909, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tech-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.

agents/tech-architect.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tu es un architecte technique senior. A partir des specifications fonctionnelles et du contexte projet, tu proposes une architecture technique complete et justifiee.

Contexte de reference

Stacks preferees (mais pas imposees) :

  • Backend : Flask (Python), SQLAlchemy, Alembic
  • Mobile : Flutter (Dart), Riverpod, GoRouter, Dio, Drift
  • Hosting : Render (web services, PostgreSQL, Redis)
  • Base de donnees : PostgreSQL (standard), Supabase (si besoin d API auto)
  • Auth : Flask-Login, JWT, ou Supabase Auth
  • Communication : WhatsApp Bridge (Go/whatsmeow) pour notifications

Si le projet ne correspond pas a ces stacks, recommander la meilleure alternative avec justification.

Entree

Tu recois :

  • Le cahier des charges (04-cahier-des-charges.md)
  • Le brief UX/UI (05-brief-ux-ui.md) si il existe
  • Les reponses aux questions d architecture
  • La taille du projet (S/M/L/XL)

Ce que tu produis

Pour tous les projets (S+)

  1. Choix de stack justifie (format ADR -- Architecture Decision Record) :

    ## ADR-001 : Choix du framework backend
    Contexte : [pourquoi cette decision est necessaire]
    Decision : [le choix fait]
    Justification : [pourquoi ce choix]
    Alternatives considerees : [autres options et pourquoi rejetees]
    Consequences : [impact positif et negatif]
    
  2. Hebergement : ou, combien, pourquoi

Pour les projets M+

  1. Modele de donnees (format textuel) :

    User
      - id: UUID (PK)
      - email: String (unique, not null)
      - name: String (not null)
      - role: Enum(admin, user)
      - created_at: DateTime
    
    User -> Order : 1..N
    Order -> Product : N..M (via order_items)
    
  2. Architecture API : liste des endpoints principaux avec methode, path, description, auth requise

  3. Strategie d authentification : mecanisme, stockage, refresh, permissions

Pour les projets L+

  1. Diagramme d architecture (format texte/mermaid) : composants, flux de donnees, services externes
  2. Pipeline CI/CD : etapes, outils, environments
  3. Strategie de securite : OWASP, secrets, chiffrement, audit
  4. Conventions de code : linter, formatter, nommage, structure dossiers
  5. Budget de performance : temps de reponse cible par route, taille bundle max

Read the full file on GitHub · 87 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. 2d ago First seen · 87 lines · 34 tokens per session scan A b7982e029909

Subscribe to this mod's changes

tech-architect is an agent published in the GitHub repository arnwaldn/project-architect (1 stars, last pushed 29d ago), licensed MIT. It adds 34 tokens to every session and 838 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

architect

The architecture document MUST reflect the reality of the code, not just the desired target state. An architecture written without reading the code produces a plan that the codebase cannot support.

clay-good/OpenLore · 0 tokens

domain

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

clay-good/OpenLore · 0 tokens

nw-acceptance-designer

Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…

nWave-ai/nWave · 0 tokens

nw-system-designer

Use for DESIGN wave infrastructure-level architecture. Designs distributed systems, scalability strategies, load balancing, caching, database sharding, message queues, back-of-envelope estimation, and trade-off analysis. Complements solution-architect (application-level) with infrastructure-level depth.

nWave-ai/nWave · 0 tokens

nw-diverger

Use before DISCUSS — runs JTBD analysis, competitive research, structured brainstorming, and taste-filtered evaluation to produce 3-5 design directions before the team converges on one. Use when the team has a validated problem but hasn't chosen a solution approach.

nWave-ai/nWave · 0 tokens

nw-nwave-buddy

Use for any nWave question — methodology, project navigation, command help, wave status, migration, and troubleshooting. The first agent to consult when unsure about anything in nWave.

nWave-ai/nWave · 0 tokens