What is arch-topology?

A guide to choosing how agents are arranged in a Kore.ai project. It compares one agent, a scripted flow, and a supervisor with specialist agents that hand work to one another.

Use it to explain an existing agent structure, choose between one agent and several specialists, inspect handoffs and delegation, and measure topology changes against real or test conversations.

Extra agents add routing decisions, boundaries between conversation context, and often more model calls. The guide uses flow graphs, session decisions, and evaluation results to decide whether that complexity is justified.

arch-topology — Skill for Codex by Koredotcom/agents-mcp-tools

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.

Any agent

npx skills add Koredotcom/agents-mcp-tools --skill arch-topology

Clone the repo

git clone --depth 1 https://github.com/Koredotcom/agents-mcp-tools

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-topology/github.svg)](https://agentmods.dev/skills/koredotcom/agents-mcp-tools/arch-topology)

Your own site

<a href="https://agentmods.dev/skills/koredotcom/agents-mcp-tools/arch-topology"><img src="https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-topology/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/skills/koredotcom/agents-mcp-tools/arch-topology"><img src="https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-topology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,669 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	$0.00090	$0.01669
Opus 5.5	$0.00036	$0.00668
Sonnet 5.5	$0.00018	$0.00334
Haiku 4.5	$0.00009	$0.00167

Measured 1mo ago against content hash 509dc6dc4738, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arch-topology 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 1mo 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.

skills/arch-topology/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Topology

Start with the smallest topology that meets the experience contract. Add an agent only when evals show the single agent failing for a reason another agent fixes. Every extra agent adds a routing decision, a context boundary and usually a model call.

Gather the evidence

debug_get_flow_graph (after debug_load_agent, or with projectId, sessionId and source: "historical") with format: "mermaid" and includeAppGraph: true.
platform_package_model on the exported package (path or files) for compiler-visible agents, tools, handoffs and diagnostics.
debug_explain_decision with type: "handoff" on real sessions to see routing decisions (pass projectId and source: "historical" for sessions that are not live).
platform_eval_runs with compare to measure a topology change instead of arguing it.

Orienting on an existing project

When the developer asks "explain this project to me", produce before any recommendation:

The full app flow graph as Mermaid.
An agent table: agent | what it owns, in plain words | how it is reached (deterministic WHEN or model routing) | tools | handoffs out with pass, summary and history | model calls on a typical turn.
One top-intent conversation, turn by turn, from a real or scripted session.
The three design choices most likely to cost latency or tokens, with evidence.

Decision guide

Ask in order and stop at the first yes:

Is it a fixed procedure (authentication, payments, compliance wording)? Use a scripted FLOW with GATHER steps, and DIGRESSIONS for side questions.
Can one agent pass the evals (one persona, one domain, a tool list it handles)? Use a single reasoning agent with tools. This is the default: cheapest and easiest to debug.
Does the user talk to distinct domains with different tools, policies or owners? Use a supervisor with specialists through HANDOFF, passing fields and small history.
Otherwise, fix the agent before adding agents: tighter instructions, fewer tools, DELEGATE for silent look-ups.

Read the full file on GitHub · 118 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 118 lines · 90 tokens per session scan A 509dc6dc4738

Subscribe to this mod's changes

arch-topology is a skill published in the GitHub repository Koredotcom/agents-mcp-tools (4 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 1,669 once invoked, about $0.0004 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 2026-10-09.

Building agents Planning

arch-topology next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
arch-topologyKoredotcom/agents-mcp-tools	Skill	4	1mo ago	MIT	A	90	Codex
imagegenopenai/codex	Skill	135k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	80k	6d ago	MIT	A	200	Claude Code, Codex
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex