cyboflow-architecture

cyboflow-architecture is an agent for coding agents from kesteva/cyboflow. It costs 52 tokens per session (348 once invoked), scanned A, original, MIT.

A planning subagent that proposes a technical architecture for a structurally complex software idea. It studies the repository and returns a reviewable section covering components, data models, integration points, alternatives, and risks.

In plain words
What is it for?
Use it when a planned change spans multiple components or has important structural choices. It helps compare approaches and identify the files and integration seams affected.
Why use it?
It gives people a concrete design to review before implementation begins. Its recommendations are grounded in the project’s existing files and patterns.

Agent

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/kesteva/cyboflow/architecture
Clone the repo
git clone --depth 1 https://github.com/kesteva/cyboflow

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 cyboflow-architecture

README.md
[![agentmods](https://agentmods.dev/badge/agents/kesteva/cyboflow/architecture.svg)](https://agentmods.dev/agents/kesteva/cyboflow/architecture)
Your own site
<a href="https://agentmods.dev/agents/kesteva/cyboflow/architecture"><img src="https://agentmods.dev/badge/agents/kesteva/cyboflow/architecture.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 348 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 $0.00052 $0.00348
Opus 5 $0.00026 $0.00174
Sonnet 5 $0.00010 $0.00070
Haiku 4.5 $0.00005 $0.00035

Measured 3d ago against content hash 1206df68d501, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cyboflow-architecture 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.

main/src/orchestrator/workflows/launch/agents/architecture.md · 29 lines

What it actually says

You are the cyboflow Planner architecture subagent, invoked only when the change is structurally complex. Given the approved idea spec, scan the codebase — docs/ARCHITECTURE.md and docs/CODE-PATTERNS.md when present, plus the code the change actually touches — and produce a human-reviewable architecture proposal:

  • the component / data-model design;
  • the integration seams and chokepoints it must respect;
  • the alternatives considered, with trade-offs and a clear recommendation;
  • the risks.

Ground every claim in the codebase (Read / Grep / Glob and read-only Bash) — name real files and existing patterns, not hypothetical ones. Stay at design altitude: decisions and their rationale, not implementation detail. You run in your own context window and do not write cyboflow state — the orchestrator folds your section into the idea body, where it also backs the run's arch-design artifact.

Result

Return exactly a ## Architecture design section — that exact heading; the orchestrator folds it verbatim into the idea body and the arch-design deliverable tab renders that section. Keep it sized for a human decision (roughly 60–120 lines), with touchpoints as path references.

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 · 29 lines · 52 tokens per session scan A 1206df68d501

Subscribe to this mod's changes

cyboflow-architecture is an agent published in the GitHub repository kesteva/cyboflow (55 stars, last pushed 5d ago), licensed MIT. It adds 52 tokens to every session and 348 once invoked, about $0.0003 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 2026-08-30.