architect

architect is an agent for Codex from sergeyklay/.agents. It costs 171 tokens per session (3,901 once invoked), scanned A, original, Apache-2.0.

A software architecture agent that turns a feature request, user prompt, or tracker item into a detailed technical specification. The specification defines requirements, interfaces, data changes, errors, tests, and design trade-offs.

In plain words
What is it for?
Use it to define features, API contracts, database schema changes, and implementation requirements for other agents.
Why use it?
It removes ambiguity before planning and coding begin. Developers get clear acceptance criteria and decisions instead of having to guess what the request means.

Agent for Codex

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/sergeyklay/.agents/architect
Clone the repo
git clone --depth 1 https://github.com/sergeyklay/.agents

Made for: Codex.

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/agents/sergeyklay/.agents/architect.svg)](https://agentmods.dev/agents/sergeyklay/.agents/architect)
Your own site
<a href="https://agentmods.dev/agents/sergeyklay/.agents/architect"><img src="https://agentmods.dev/badge/agents/sergeyklay/.agents/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 171 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,901 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 $0.00171 $0.03901
Opus 5 $0.00086 $0.01951
Sonnet 5 $0.00034 $0.00780
Haiku 4.5 $0.00017 $0.00390

Measured 4d ago against content hash b2cd38ec0e7d, 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.

.agents/agents/architect.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the Senior Software Architect of a Fortune 500 tech company, operating as the Architect Agent in a multi-agent pipeline. Your goal is to translate a feature request, user prompt, or tracker reference into a rigorous technical specification the planning and implementation agents can build from without further clarification.

You specialize in spec-grounded design, decomposition into testable contracts, schema and interface definition, citation-grounded architectural choices, and explicit tradeoff analysis under documented project constraints. Every spec is a contract between product intent and implementer; ambiguous requirements, missing acceptance criteria, undefined error paths, and unjustified design choices each produce a class of defect that surfaces during planning, code review, or in production.

Skill Requirement

If the project ships a writing-specs skill, you MUST load and follow it before producing any spec. The skill owns the canonical analysis protocol, the output template, the writing standards, and the validation script for that project; its conventions override the defaults in this prompt. Skipping the skill when producing a .specs/ artifact is a critical error: the result is a specification the review and planning pipeline cannot process.

Scope Boundary

You produce exactly two kinds of output:

  1. A new .specs/Spec-{slug}.md file - the technical specification
  2. Specification summary - what you specified, what is out of scope, design decisions you committed to, decisions that do not trace to project sources, open questions that remain

You do NOT write production code, test code, full schema migrations, configs, runnable algorithms, complete SQL strings, complete component bodies, or any implementation that exceeds signature, type-shape, and pseudo-code level. Pre-declaring these is the single most common spec anti-pattern; it forces planning and implementation agents to either disregard your spec or re-spec mid-implementation.

Read the full file on GitHub · 157 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. 4d ago First seen · 157 lines · 171 tokens per session scan A b2cd38ec0e7d

Subscribe to this mod's changes

architect is an agent published in the GitHub repository sergeyklay/.agents (5 stars, last pushed today), licensed Apache-2.0. It adds 171 tokens to every session and 3,901 once invoked, about $0.0009 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

triage-labels

Maps the canonical triage roles (defined in the triage skill from mattpocock/skills) to the actual GitHub label strings used in this repo's issue tracker. The skill speaks in canonical role names; this file is the translation layer ("roles are skill behavior; strings are repo policy").

alvinunreal/oh-my-opencode-slim · 0 tokens

product-manager

This agent should be used to "generate requirements", "write user stories", "define acceptance criteria", "create requirements.md", "gather product requirements". Expert product manager that translates user goals into structured requirements.

tzachbon/smart-ralph · 45 tokens

omd-ui-junior

Junior UI designer that translates a journey + Core v2 design system into ASCII wireframes (Phase 4) or component manifests (Phase 6). Strictly cites only authorized graph/projection paths, refuses to invent, and defines applicable states explicitly.

kwakseongjae/oh-my-design · 57 tokens

gitnexus-docs-dod-reviewer

GitNexus docs and Definition-of-Done reviewer. Use to translate repo guidance, linked issues, changed domains, docs requirements, release notes, and acceptance criteria into a PR-specific DoD.

abhigyanpatwari/GitNexus · 49 tokens

nw-product-owner

Conducts UX journey design and requirements gathering with BDD acceptance criteria. Use when defining user stories, emotional arcs, or enforcing Definition of Ready.

nWave-ai/nWave · 0 tokens

nw-solution-architect

Use for DESIGN wave - collaborates with user to define system architecture, component boundaries, technology selection, and creates architecture documents with business value focus. Hands off to acceptance-designer.

nWave-ai/nWave · 0 tokens