idea-refine

idea-refine is a skill for Claude Code, Codex from vanja-emichi/a0_agent_skills. It costs 70 tokens per session (2,093 once invoked), scanned A, original, MIT.

A structured method for turning a rough software idea into a clearer, testable concept. It uses brainstorming followed by narrowing and evaluation.

In plain words
What is it for?
Exploring possible features or products, refining vague requests, comparing directions, and stress-testing a plan before writing a specification.
Why use it?
It helps expose assumptions and weaknesses before time and resources are committed to implementation.

Skill for Claude CodeCodex

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

Good fit Exploring possible features or products, refining vague requests, comparing directions, and stress-testing a plan before writing a specification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vanja-emichi/a0_agent_skills/idea-refine
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 vanja-emichi/a0_agent_skills --skill idea-refine
Clone the repo
git clone --depth 1 https://github.com/vanja-emichi/a0_agent_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 idea-refine

README.md
[![agentmods](https://agentmods.dev/badge/skills/vanja-emichi/a0_agent_skills/idea-refine/github.svg)](https://agentmods.dev/skills/vanja-emichi/a0_agent_skills/idea-refine)
Your own site
<a href="https://agentmods.dev/skills/vanja-emichi/a0_agent_skills/idea-refine"><img src="https://agentmods.dev/badge/skills/vanja-emichi/a0_agent_skills/idea-refine/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 idea-refine

Your own site · 80×15
<a href="https://agentmods.dev/skills/vanja-emichi/a0_agent_skills/idea-refine"><img src="https://agentmods.dev/badge/skills/vanja-emichi/a0_agent_skills/idea-refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,093 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 $0.00070 $0.02093
Opus 5 $0.00035 $0.01046
Sonnet 5 $0.00014 $0.00419
Haiku 4.5 $0.00007 $0.00209

Measured 10d ago against content hash df52a9b20054, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

idea-refine 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/idea-refine.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/idea-refine/SKILL.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Idea Refine

Refines raw ideas into sharp, actionable concepts worth building through structured divergent and convergent thinking.

Supporting files: After loading this skill, the file tree above shows the skill directory path. Use text_editor:read (not skills_tool:read_file) to open supporting files: frameworks.md, refinement-criteria.md, and examples.md. Replace {skill_path} below with the path shown in the file tree.

Overview

Refines raw ideas into sharp, actionable concepts worth building through structured divergent and convergent thinking.

When to Use

  • Starting from a vague idea or gut feeling
  • Brainstorming a new feature, product, or process improvement
  • Exploring design space before writing a spec
  • Stress-testing a plan before committing resources
  • When "I want to build X" needs to become "Here is what X actually is and why"

When NOT to use: You already have a clear spec with acceptance criteria. Use spec-driven-development instead.

Setup

To initialize the ideas output directory, run the setup script using code_execution_tool:

# The skill path is shown in the file tree when this skill is loaded.
# Replace <skill_path> with the actual path shown above.
bash <skill_path>/scripts/idea-refine.sh

This creates docs/ideas/ in the current working directory if it doesn't exist.

Output

The final output is a markdown one-pager saved to docs/ideas/[idea-name].md (after user confirmation), containing:

  • Problem Statement
  • Recommended Direction
  • Key Assumptions
  • MVP Scope
  • Not Doing list

Process

This skill is primarily an interactive dialogue. When the user invokes this skill with an idea (from their message), guide them through three phases. Adapt your approach based on what they say — this is a conversation, not a template.

Phase 1: Understand & Expand (Divergent)

Goal: Take the raw idea and open it up.

  1. Restate the idea as a crisp "How Might We" problem statement. This forces clarity on what's actually being solved.

Read the full file on GitHub · 234 lines

Files

What ships with it

4 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 · 234 lines · 70 tokens per session scan A df52a9b20054

Subscribe to this mod's changes

idea-refine is a skill published in the GitHub repository vanja-emichi/a0_agent_skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 2,093 once invoked, about $0.0003 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.