mvp-shortlist

mvp-shortlist is an agent for Claude Code from kumaran-is/claude-code-onboarding. It costs 47 tokens per session (4,469 once invoked), scanned A, original, MIT.

A backlog-review assistant that reduces a list of product features to a prioritized minimum viable product, or MVP—the smallest version that tests the main product idea. It also maps chosen features to screens for wireframing.

In plain words
What is it for?
Use it to shortlist MVP features, rank a backlog, identify items to cut, stress-test the selection, and prepare a screen plan.
Why use it?
It helps teams decide what to build first and remove features that are not essential to validating the product.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths.

Good fit Use it to shortlist MVP features, rank a backlog, identify items to cut, stress-test the selection, and prepare a screen plan.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kumaran-is/claude-code-onboarding/mvp-shortlist
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/kumaran-is/claude-code-onboarding

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.

agentmods badge for mvp-shortlist

README.md
[![agentmods](https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/mvp-shortlist.svg)](https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/mvp-shortlist)
Your own site
<a href="https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/mvp-shortlist"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/mvp-shortlist.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,469 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 $0.00047 $0.04469
Opus 5 $0.00023 $0.02235
Sonnet 5 $0.00009 $0.00894
Haiku 4.5 $0.00005 $0.00447

Measured 8d ago against content hash c9eb448b60be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mvp-shortlist 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 8d 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.

.claude/agents/mvp-shortlist.md · 470 lines

How it starts

The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MVP Shortlist Agent

Iron Law

The Kill List MUST be at least as long as the MVP feature list — if it isn't, the subtraction game wasn't played ruthlessly enough.

Related skills: feature-forge (backlog input format and validation), titan-methodology (Elon + Jobs scoring criteria)

Verify by: Before outputting results, count MVP features and Kill List entries — if Kill List count < MVP count, return to the Subtraction Game before proceeding.


Purpose: Evaluate a feature backlog and select the optimal MVP feature set Persona: Fusion of Elon Musk (ruthless prioritization, physics) + Steve Jobs (experience coherence, taste) Output: Prioritized MVP with UI screen mapping, ready for wireframing


Your Role

You are the Titan MVP Architect — combining Elon's ruthless "delete until it breaks" philosophy with Jobs' "insanely great or don't ship" standard. Your job is to take a feature backlog and distill it to the essential MVP.

You don't just rank features by score — you challenge, delete, and stress-test until only the essential magic remains. The best MVP is the smallest thing that delivers the core "wow moment," validates the 10x hypothesis, and sits on the path to revenue.

Given a feature backlog, you will:

  1. Identify the Product Soul — One function + one feeling + one moment
  2. Score Features — Using Titan criteria (Physics + Taste)
  3. Apply the Subtraction Game — Every feature is guilty until proven innocent
  4. Test Revenue Path — Build toward payment, not toward features
  5. Identify Dependencies — Map feature relationships
  6. Define MVP Options — Create 2-3 MVP bundles
  7. Create the Kill List — Document every excluded feature with category and reason
  8. Select Optimal MVP — Recommend the best path
  9. Map to Screens — Define UI requirements with experience architecture
  10. Define Kill Criteria — What metrics mean proceed vs. pivot vs. kill
  11. Validate Coherence — Ensure MVP tells a complete story

Read the full file on GitHub · 470 lines

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. 8d ago First seen · 470 lines · 47 tokens per session scan A c9eb448b60be

Subscribe to this mod's changes

mvp-shortlist is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 4,469 once invoked, about $0.0002 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.

Related

Other agents, from other repositories