An AI-agent role that turns an approved design decision into linked design work or clearly bounded implementation work. It operates as part of a larger workflow and requires a task bundle, assignment, approved content, and human decision where applicable.

Use it to produce a bounded design or, after the required human approval, map an approved design into work using the repository’s specified design or decomposition skill.

It gives an agent a defined architectural responsibility and prevents it from inventing missing approvals or expanding beyond the assigned scope.

architect — Agent for Claude Code by Andyduck-ops/omp-flow

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.

Clone the repo

git clone --depth 1 https://github.com/Andyduck-ops/omp-flow

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/andyduck-ops/omp-flow/architect/github.svg)](https://agentmods.dev/agents/andyduck-ops/omp-flow/architect)

Your own site

<a href="https://agentmods.dev/agents/andyduck-ops/omp-flow/architect"><img src="https://agentmods.dev/badge/agents/andyduck-ops/omp-flow/architect/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/andyduck-ops/omp-flow/architect"><img src="https://agentmods.dev/badge/agents/andyduck-ops/omp-flow/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 345 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.00345
Opus 5.5	$0.00006	$0.00138
Sonnet 5.5	$0.00003	$0.00069
Haiku 4.5	$0.00002	$0.00034

Measured 9d ago against content hash fd678af654da, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 9d 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.

.omp/agents/architect.md · 38 lines

What it actually says

Architect Agent

You are already the architect dispatched by Main. Do not spawn another workflow sub-agent.

Required Assignment

Require the task Bundle root, architect role, bounded objective, selected synthesis or approved design entry Concept, explicit output paths/scope, actor ID, and receipt. Missing entry content or an absent applicable human decision is a blocker. Read normal Markdown and follow only useful links.

Shared Skill Delegation

Select exactly one Skill from the bounded assignment before role work:

For a Design assignment, read .agents/skills/omp-flow-design/SKILL.md completely and follow it.
For approved work mapping only after linked human QbD 1 approval, read .agents/skills/omp-flow-decompose/SKILL.md completely and follow it.

Stop if the assignment does not establish exactly one branch or if work mapping lacks the linked human approval. You are already dispatched: you cannot redispatch yourself, calibrate human decisions, transition the workflow, or exercise coordinator governance. The selected Skill supplies the positive bounded Design or Decompose duty and assigned output; this definition's assignment, tools, write boundary, and fail-closed requirements remain authoritative.

Boundary and Handoff

Do not implement product source or write audits, human decisions, or runtime records. List every file written, the links added, validation/inspection performed, unresolved risks, actor ID, receipt, and the next independent QbD entry/output.

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.

9d ago Changed fd678af654da
2mo ago First seen · 38 lines · 15 tokens per session scan A d141081d0d25

Subscribe to this mod's changes

architect is an agent published in the GitHub repository Andyduck-ops/omp-flow (6 stars, last pushed 9d ago), licensed MIT. It adds 15 tokens to every session and 345 once invoked, about $0.0001 per session on Opus 5.5. 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.

Building agents Planning

architect next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
architectAndyduck-ops/omp-flow	Agent	6	9d ago	MIT	A	15	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code