venture-architect

venture-architect is a skill for Claude Code, Codex from gyanranjan/polyagent-skills. It costs 134 tokens per session (3,453 once invoked), scanned A, original, MIT.

An end-to-end role that turns a raw startup or product idea into a structured set of planning and presentation materials.

In plain words
What is it for?
Use it when turning a new idea into research, a product plan, system and engineering plans, venture documents, and a pitch deck.
Why use it?
Early ideas usually lack research, product definition, technical planning, and a clear investor story. This role connects those stages into one workflow.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when turning a new idea into research, a product plan, system and engineering plans, venture documents, and a pitch deck.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gyanranjan/polyagent-skills/venture-architect
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 gyanranjan/polyagent-skills --skill venture-architect
Clone the repo
git clone --depth 1 https://github.com/gyanranjan/polyagent-skills

Made for: Claude Code, 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 venture-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/venture-architect/github.svg)](https://agentmods.dev/skills/gyanranjan/polyagent-skills/venture-architect)
Your own site
<a href="https://agentmods.dev/skills/gyanranjan/polyagent-skills/venture-architect"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/venture-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.

agentmods 80×15 button for venture-architect

Your own site · 80×15
<a href="https://agentmods.dev/skills/gyanranjan/polyagent-skills/venture-architect"><img src="https://agentmods.dev/badge/skills/gyanranjan/polyagent-skills/venture-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,453 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00134 $0.03453
Opus 5 $0.00067 $0.01726
Sonnet 5 $0.00027 $0.00691
Haiku 4.5 $0.00013 $0.00345

Measured 10d ago against content hash 9f112f1510fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

venture-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 10d 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/venture-architect/SKILL.md · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Venture Architect

Purpose

Transform a raw idea into a complete, production-grade set of venture artifacts in one autonomous execution loop. The skill chains six specialist roles — Research Analyst, Entrepreneur, Product Manager, Systems Architect, Engineering Planner, and Deck Creator — each producing a dedicated document. The final output is a fully scaffolded project directory ready for implementation handoff.

When to Use

  • User says "this is an idea", "I have an idea", "here's a concept"
  • User says "turn this into a venture" or "take this from concept to pitch"
  • User presents a raw startup, product, or business idea and expects full analysis
  • User asks for a complete venture package (feasibility through pitch deck)
  • User wants to go from zero to a structured, investor-ready artifact set

When NOT to Use

  • User already has formal requirements and only needs implementation (use implementation-sketch)
  • User only wants a pitch deck from existing content (use deck-creator)
  • User only wants competitive research (use research-analyst directly)
  • User wants to iteratively refine an MVP with interactive Q&A (use idea-to-mvp)
  • User wants to write code immediately (that's coding, not venture design)

Inputs

Required:

  • Raw idea — any amount of text describing a concept, product, or venture

Optional:

  • Project name — if not provided, the agent will derive one from the idea
  • Target market or industry context
  • Known technical constraints or preferences
  • Budget or timeline context
  • Existing competitors the user is already aware of

Process

No-Nudge Policy

Do NOT ask the user for permission before creating documents. Instead, announce what you are doing:

  • "I am now generating the Feasibility Report based on the identified technical risks."
  • "Moving to the Entrepreneur role — generating the Business Requirement Document."
  • "The SRS is complete. Proceeding to the Engineering Planner role."

Only ask the user when:

  • Private business information is required and cannot be inferred
  • Domain clarification is impossible without input
  • The project scope is fundamentally ambiguous

Read the full file on GitHub · 331 lines

Files

What ships with it

6 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.

  1. 10d ago First seen · 331 lines · 134 tokens per session scan A 9f112f1510fa

Subscribe to this mod's changes

venture-architect is a skill published in the GitHub repository gyanranjan/polyagent-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 134 tokens to every session and 3,453 once invoked, about $0.0007 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 skills, from other repositories

frontmcp-guides

Tutorials, end-to-end walkthroughs, and complete reference projects for FrontMCP. Use when you want a getting-started guide, a full worked example, or to learn best practices by following a step-by-step build rather than a single API reference. Includes a beginner weather-API server (tool plus static resource, Zod…

agentfront/frontmcp · 157 tokens

design-doc

A set of rules and templates for creating and reviewing product design documents in the ued/ directory. It covers documents ranging from strategy and requirements to architecture, detailed design, and validation.

reddishz/designdoc · 87 tokens

idea-validator

Giúp đánh giá một ý tưởng có đáng thử hay không cho mục đích kinh doanh hoặc học tập, dựa trên bằng chứng, nguồn lực thực tế và một bước thử có giới hạn. Dùng khi cần xem nhanh, phân tích đầy đủ, so sánh ý tưởng hoặc xem lại báo cáo cũ.

itsddvn/skills-shared · 68 tokens

ti-founder

Founder profile template, creation questions, section definitions, and fit question guidance for TweakIdea evaluations.

eph5xx/tweakidea · 22 tokens

ti-report

Jinja2 templates + CSS + data contract for TweakIdea evaluation reports.

eph5xx/tweakidea · 18 tokens

mvp-agent-context

Generate Codex-first agent context files for a Web MVP. Use after the PRD and Technical Blueprint exist when the user needs AGENTS.md, REVIEW-CHECKLIST.md, and agentdocs for project brief, requirements, tech stack, page map, data model, build tasks, testing, and reusable prompts.

kornpng/web-mvp-blueprint-kit · 67 tokens