architect

A guided design-and-build command for creating a new app or service from the beginning. It gathers requirements, compares architecture options, chooses a technology stack, defines API contracts when needed, and records important decisions.

In plain words
What is it for?
It is for starting greenfield applications or services, choosing between architecture approaches, documenting decisions, designing APIs, and carrying a project through planning, implementation, review, and testing.
Why use it?
It helps turn an idea into a documented technical plan and a working project without skipping requirements, design decisions, or verification.

Command

Part of the hydraia plugin — 16 skills, 15 commands, 26 agents, 4 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/jdanigo/hydraia/architect
Clone the repo
git clone --depth 1 https://github.com/jdanigo/hydraia

Or install hydraia, the plugin that ships this one along with the rest of its 16 skills, 15 commands, 26 agents, 4 hooks.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 261 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 $0.00032 $0.00261
Opus 5 $0.00016 $0.00130
Sonnet 5 $0.00006 $0.00052
Haiku 4.5 $0.00003 $0.00026

Measured 3d ago against content hash a4161832494a, 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 3d 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.

commands/architect.md · 11 lines

What it actually says

Invoke the hydraia skill forcing the Phase -1 route to greenfield. Run the greenfield-architect skill: elicit requirements one question at a time (problem, honest scale, team/constraints, non-functionals, integrations), dispatch the architect + code-architect agents for 2-3 architecture shapes with a recommendation (microservices only with evidence — monolith is the default), confirm the stack with rationale, design the API contract via the api-design skill when an API exists, and record every load-bearing decision as an ADR under docs/hydraia/adr/ (or the resolved artifacts base — the external dir when chosen at the storage gate). Then continue the FULL pipeline (Phases 0-6): spec referencing the ADRs, plan, execution with the matching stack-pattern skill, double review, verify.

To stop at the frozen plan instead of building, use /hydraia:plan with the same idea after the architecture dialogue.

Request: $ARGUMENTS

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. 3d ago First seen · 11 lines · 32 tokens per session scan A a4161832494a

Subscribe to this mod's changes

architect is a command published in the GitHub repository jdanigo/hydraia (8 stars, last pushed 13d ago), licensed MIT. It adds 32 tokens to every session and 261 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.