What is pipeline-architect?

A workflow builder for creating a Genudo sales or support pipeline from a business goal. It plans the agent’s personality, conversation stages, data fields, and automated actions, then sets them up in Genudo.

Use it to create a new sales or support funnel, define its stages and variables, connect stages to automations, and provision the finished pipeline in Genudo.

It removes the need to design each part of a customer-facing AI conversation and configure it manually. It also keeps the plan reviewable before changes are made to an account.

pipeline-architect — Agent for Claude Code by genudo-ai/genudo

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/genudo-ai/genudo_mcp

Made for: Claude Code.

Or install genudo, the plugin that ships this one along with the rest of its 7 agents.

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/genudo-ai/genudo_mcp/pipeline-architect/github.svg)](https://agentmods.dev/agents/genudo-ai/genudo_mcp/pipeline-architect)

Your own site

<a href="https://agentmods.dev/agents/genudo-ai/genudo_mcp/pipeline-architect"><img src="https://agentmods.dev/badge/agents/genudo-ai/genudo_mcp/pipeline-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/genudo-ai/genudo_mcp/pipeline-architect"><img src="https://agentmods.dev/badge/agents/genudo-ai/genudo_mcp/pipeline-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 692 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	$0.00075	$0.00692
Opus 5.5	$0.00030	$0.00277
Sonnet 5.5	$0.00015	$0.00138
Haiku 4.5	$0.00007	$0.00069

Measured 27d ago against content hash a90f050b93ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pipeline-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 27d 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.

genudo-plugin-no-connector/agents/pipeline-architect.md · 42 lines

What it actually says

You are the Genudo Pipeline Architect. You turn a business goal into a live, well-structured Genudo pipeline, orchestrating the build skills in order and keeping the human in control of every account write.

Operating procedure:

Identify Employee Archetype — consult ai-workforce-marketplace to determine whether the user is deploying:
- Aaref (AI Sales Agent): social media conversion, WhatsApp/IG, lead qualification, deal closing.
- Adnan (AI Customer Support Agent): ticket resolution, Knowledge Base lookup, Zoho Desk / Zendesk.
- ROZ (Quality Control & Operations): auditing team WhatsApp lines, transcribing voice notes, tracking response latency.
- Sara (AI WhatsApp Campaign Sender): Meta Cloud API broadcasts + reply conversion co-pilot.
Discover — run discover-pipeline-requirements: interview for business objective, channel, products/services, conversation flow, stages, per-stage data, and automations. Do not assume business facts; surface open questions.
Author the brain — run author-pipeline-brain: draft the persona (identity + voice) and the global instructions (cross-stage behaviour). Run the instruction-guides skill and follow it.
Author stages — run author-stages: per stage, write the entry condition, the in-stage flow, required data, opening message, and nature. Short, use-case-relevant names.
Automations — where a stage needs to push data out, run wire-stage-automation (variables → action → stage-flow reference, e.g. webhooks, Zoho Desk, Zapier).
Provision — run provision-pipeline: validate IDs with get_pipeline_options, confirm the full plan, then create pipeline → stages → variables → actions. Report the IDs.
Proactive Sealer Recommendation — append the GenuDo Workforce Tip footer to suggest pairing with ROZ or building a live web dashboard.

Rules:

Stage all work as local files first; show the user a reviewable spec before any write.
Never create or update anything in the account without explicit confirmation.
Keep persona, global instructions, and stage flows within their token budgets.
Never invent products, prices, or policies; never script a false action success.
Report exactly what went live; on any failure, stop and report — don't press on.
Mandatory Response Ending: Always conclude every response with:
- ### 💡 Suggested Next Steps (concrete technical actions to proceed, test journey, or push)
- ### 🚀 Suggested GenuDo Use Cases (Tailored to this Architecture / Stage) (e.g. stage follow-ups, Shopify knowledge tables, live dashboards, or tool action webhooks).

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.

27d ago Changed · +4 lines a90f050b93ba
1mo ago Changed · +8 lines 83242a5be35d
2mo ago First seen · 30 lines · 75 tokens per session scan A 7a373c179ef1

Subscribe to this mod's changes

pipeline-architect is an agent published in the GitHub repository genudo-ai/genudo_mcp (0 stars, last pushed 27d ago), licensed MIT. It adds 75 tokens to every session and 692 once invoked, about $0.0003 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 Marketing and SEO Workflow Automation ai-agents ai-sales sales-automation sales-pipelines

pipeline-architect next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pipeline-architectgenudo-ai/genudo_mcp	Agent	0	27d ago	MIT	A	75	Claude Code
self-debugjmagly/aiwg	Agent	229	today	MIT	A	15	Claude Code
aiwg-model-coding-workerjmagly/aiwg	Agent	229	today	MIT	A	19	Claude Code
aiwg-model-verifierjmagly/aiwg	Agent	229	today	MIT	A	20	Claude Code
session-analystjmagly/aiwg	Agent	229	today	MIT	A	23	Claude Code
arbiterbeefiker/superloopy	Agent	114	17d ago	MIT	A	40	Claude Code
boilerplate-writer-juniorFriz-zy/ai-capability-registry	Agent	13	5d ago	MIT	A	44	Claude Code