solo-feature-ideas

solo-feature-ideas is a command for Claude Code from ericvtheg/solo-founder-toolkit. It costs 12 tokens per session (1,122 once invoked), scanned A, original, MIT.

A command that examines a codebase and proposes feature ideas ranked with a framework based on effort, impact, and confidence.

In plain words
What is it for?
It is for identifying and comparing three to five feature opportunities before deciding what to build next.
Why use it?
It connects possible features to the product's existing code, users, documentation, and evidence of demand.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the solo-founder-toolkit plugin — 3 skills, 4 commands, 1 agent, 1 MCP server shipped together

Good fit It is for identifying and comparing three to five feature opportunities before deciding what to build next.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ericvtheg/solo-founder-toolkit/solo-feature-ideas
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/ericvtheg/solo-founder-toolkit

Made for: Claude Code.

Or install solo-founder-toolkit, the plugin that ships this one along with the rest of its 3 skills, 4 commands, 1 agent, 1 MCP server.

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 solo-feature-ideas

README.md
[![agentmods](https://agentmods.dev/badge/commands/ericvtheg/solo-founder-toolkit/solo-feature-ideas/github.svg)](https://agentmods.dev/commands/ericvtheg/solo-founder-toolkit/solo-feature-ideas)
Your own site
<a href="https://agentmods.dev/commands/ericvtheg/solo-founder-toolkit/solo-feature-ideas"><img src="https://agentmods.dev/badge/commands/ericvtheg/solo-founder-toolkit/solo-feature-ideas/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 solo-feature-ideas

Your own site · 80×15
<a href="https://agentmods.dev/commands/ericvtheg/solo-founder-toolkit/solo-feature-ideas"><img src="https://agentmods.dev/badge/commands/ericvtheg/solo-founder-toolkit/solo-feature-ideas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,122 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 $0.00012 $0.01122
Opus 5 $0.00006 $0.00561
Sonnet 5 $0.00002 $0.00224
Haiku 4.5 $0.00001 $0.00112

Measured 9d ago against content hash e63e96abfaca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

solo-feature-ideas 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 9d 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.

plugins/solo-founder-toolkit/commands/solo-feature-ideas.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze the codebase to identify 3-5 high-impact feature opportunities that users will deeply care about. Use the solo-decision-framework skill to evaluate each feature with the LIC rubric (Lift, Impact, Conviction). Present features ranked by score.

Analysis Steps

1. Understand the Product

Read key files to understand what this product does:

  • README, documentation, or marketing copy
  • Main application files (entry points, core logic)
  • Data models (what user data is stored tells you what the product does)
  • Configuration files reveal tech stack and integrations

Answer:

  • What problem does this solve for users?
  • Who is the target user and what do they care about?
  • What's the core user workflow?
  • How does this make money (or plan to)?

2. Find Sources of User Insight

Look for evidence of what users actually want:

Documentation sources:

  • README roadmap or future plans
  • CHANGELOG for recent priorities
  • Issue templates or contributing guides
  • Product documentation gaps

User feedback sources:

  • GitHub issues (open and closed)
  • TODO/FIXME comments mentioning user requests
  • Support-related code comments
  • Feature flags or A/B tests in progress

Metrics and analytics:

  • Analytics events being tracked (what's measured = what matters)
  • Conversion funnels in code
  • Error tracking and monitoring
  • Performance monitoring focus areas

Business signals:

  • Pricing tiers and what unlocks them
  • Onboarding flow structure
  • Email templates (what communication exists?)
  • Integration points (what tools do users connect?)

3. Identify User-Centered Opportunities

Focus on features users will deeply value, not technical improvements.

Ask yourself:

  • What user pain point does this solve?
  • What prevents users from getting value faster?
  • What stops users from inviting others or paying more?
  • What makes users churn or get frustrated?
  • What do competitors offer that this doesn't?

Generate 3-5 specific, user-focused features:

  • Not "refactor exports" → "Let users export to Excel so they can share with their team"
  • Not "add OAuth" → "Let users sign in with Google so onboarding is faster"
  • Not "improve notifications" → "Send users weekly summaries so they stay engaged"

Read the full file on GitHub · 156 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. 9d ago First seen · 156 lines · 12 tokens per session scan A e63e96abfaca

Subscribe to this mod's changes

solo-feature-ideas is a command published in the GitHub repository ericvtheg/solo-founder-toolkit (8 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 1,122 once invoked, about $0.0001 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.