architect

architect is a command for Claude Code from jeet129/praxis. It costs 19 tokens per session (386 once invoked), scanned A, original, MIT.

An architecture-planning command for Phase B of a project workflow. It covers system structure, APIs, data, reliability, security, and project phases, then subjects the design to a challenge review before approval.

In plain words
What is it for?
Use it to create architecture decision records and diagrams, define API and data designs, model threats, plan delivery phases, and prepare the architecture sign-off gate.
Why use it?
It exposes design risks around scale, security, cost, operations, and reliability before implementation begins.

Command for Claude Code

Part of the praxis plugin — 105 skills, 12 commands, 17 agents, 6 hooks shipped together

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 commands/jeet129/praxis/architect
Clone the repo
git clone --depth 1 https://github.com/jeet129/praxis

Made for: Claude Code.

Or install praxis, the plugin that ships this one along with the rest of its 105 skills, 12 commands, 17 agents, 6 hooks.

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.

agentmods badge for architect

README.md
[![agentmods](https://agentmods.dev/badge/commands/jeet129/praxis/architect.svg)](https://agentmods.dev/commands/jeet129/praxis/architect)
Your own site
<a href="https://agentmods.dev/commands/jeet129/praxis/architect"><img src="https://agentmods.dev/badge/commands/jeet129/praxis/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 386 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 $0.00019 $0.00386
Opus 5 $0.00010 $0.00193
Sonnet 5 $0.00004 $0.00077
Haiku 4.5 $0.00002 $0.00039

Measured 4d ago against content hash a96d907e0730, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

.claude/commands/architect.md · 30 lines

What it actually says

Start Phase B. Activate the Solution Architect agent. Run the architecture skill sequence:

  1. domain-discovery (if not already done in Phase A) — bounded contexts, ubiquitous language.
  2. architecture-pattern-selection — monolith vs services vs event-driven; data stores; sync vs async.
  3. api-design — OpenAPI spec scaffold; versioning strategy.
  4. data-modeling — schema + multi-tenant scoping if applicable.
  5. resilience-patterns — circuit breaker, retry, bulkhead per NFR availability target.
  6. distributed-systems-patterns (if distributed) — CAP/PACELC + idempotency + saga/outbox.
  7. multi-tenancy (if is_multi_tenant) — silo / pool / bridge model.
  8. threat-modeling — STRIDE + trust boundaries + data flows.
  9. project-phasing — phased roadmap.

Output ADRs to .project/decision/; diagrams to .project/working/architecture/.

Then spawn Architecture Challenger. Run all 5 sub-personas (scale / security / cost / operations / reliability). Produce challenge report (MANDATORY).

For each Challenger finding:

  • ACCEPT → SA updates the design.
  • OVERRIDE → SA writes ADR with rationale; triggers challenger_objection_override gate.

Prep the architecture_sign_off gate evidence pack: architecture decision + ADR + C4 diagrams + challenge report (MANDATORY) + phased roadmap. Show me before approving.

Common rationalizations to ignore:

  • "The architecture is obvious." → the Challenger finds what the SA missed. Run it.
  • "Threat modeling at code time is enough." → STRIDE at architecture time catches what OWASP scans can't.
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. 4d ago First seen · 30 lines · 19 tokens per session scan A a96d907e0730

Subscribe to this mod's changes

architect is a command published in the GitHub repository jeet129/praxis (7 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 386 once invoked, about $0.0001 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.