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 agentmods add agents/arnwaldn/project-architect/tech-architectgit clone --depth 1 https://github.com/arnwaldn/project-architectWhat 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 | $0.00034 | $0.00838 |
| Opus 5 | $0.00017 | $0.00419 |
| Sonnet 5 | $0.00007 | $0.00168 |
| Haiku 4.5 | $0.00003 | $0.00084 |
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.
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+)
-
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] -
Hebergement : ou, combien, pourquoi
Pour les projets M+
-
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) -
Architecture API : liste des endpoints principaux avec methode, path, description, auth requise
-
Strategie d authentification : mecanisme, stockage, refresh, permissions
Pour les projets L+
- Diagramme d architecture (format texte/mermaid) : composants, flux de donnees, services externes
- Pipeline CI/CD : etapes, outils, environments
- Strategie de securite : OWASP, secrets, chiffrement, audit
- Conventions de code : linter, formatter, nommage, structure dossiers
- Budget de performance : temps de reponse cible par route, taille bundle max
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 First seen · 87 lines · 34 tokens per session scan A b7982e029909
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.
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.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
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)…
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.
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.
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.