idea-lab

idea-lab is a skill for Claude Code from JuanMarchetto/agent-skills. It costs 104 tokens per session (925 once invoked), scanned A, original, MIT.

A reusable Idea Lab workflow for generating many project ideas, filtering weaker ones, evaluating the strongest with several reviewers, and ranking the results.

In plain words
What is it for?
Use it to explore ideas from a context, compare finalists, inspect evaluation details, and optionally hand the winner to a build workflow.
Why use it?
It turns open-ended brainstorming into a staged process with screening and comparison before choosing a direction.

Skill for Claude Code

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

Part of the idea-lab plugin — 1 skill, 1 command shipped together

Good fit Use it to explore ideas from a context, compare finalists, inspect evaluation details, and optionally hand the winner to a build workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/juanmarchetto/agent-skills/idea-lab
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 JuanMarchetto/agent-skills --skill idea-lab
Clone the repo
git clone --depth 1 https://github.com/JuanMarchetto/agent-skills

Made for: Claude Code.

Or install idea-lab, the plugin that ships this one along with the rest of its 1 skill, 1 command.

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-lab

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/juanmarchetto/agent-skills/idea-lab"><img src="https://agentmods.dev/badge/skills/juanmarchetto/agent-skills/idea-lab.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 925 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 $0.00104 $0.00925
Opus 5 $0.00052 $0.00463
Sonnet 5 $0.00021 $0.00185
Haiku 4.5 $0.00010 $0.00093

Measured 6d ago against content hash ae712467b1c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

idea-lab 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 6d 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/idea-lab/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Idea Lab — Automated Idea Generation & Evaluation

Generate multiple diverse ideas, evaluate the best ones with 6-evaluator scoring, rank and surface the winners.

How It Works

/idea-lab "FinTech hackathon, 48h, team of 2, must use AI"
        │
        ▼
  Phase 0: Bootstrap ─── config.json + context setup
        │
        ▼
  Phase 1: Generate ─── N diverse ideas via forced divergence axes
        │
        ▼
  Phase 2: Pre-screen ─── quick 1-agent score per idea, filter weak ones
        │
        ▼
  ══ PRE-SCREEN DASHBOARD ══ see all ideas ranked by estimate
        │
        ▼
  Phase 3: Deep Eval ─── top-K ideas → /architect (6 evaluators each)
        │
        ▼
  ══ FINAL DASHBOARD ══ comparative matrix, top recommendation
        │
        ▼
  [expand N] — full evaluation details
  [build N]  — launch /founder-mode with the winner
  [refine]   — adjust context, generate more
  [stop]     — save and exit

Phases

Phase What It Does Agent
0 - Bootstrap Config generation, context capture bootstrapper.md
1 - Generate N ideas with forced diversity (SCAMPER, cross-domain, axis rotation) generator.md
2 - Pre-screen Quick 1-agent score per idea, filters below threshold prescreener.md
3 - Deep Eval Top-K ideas evaluated via /architect (6 parallel evaluators each) deep-evaluator.md
4 - Ranking Comparative matrix, scenario recommendations, top pick ranker.md

Diversity Engine

Ideas are forced to diverge across configurable axes:

  • B2B SaaS, B2C consumer, open-source tool, educational, mobile-first
  • SCAMPER method applied per idea
  • Cross-domain analogies forced for at least 2 ideas
  • Anti-obvious filter removes generic suggestions

Config

Generated at .idea-lab/config.json during bootstrap:

  • ideaCount: how many to generate (default 5, max 20)
  • topK: how many advance to deep evaluation (default 3)
  • minScore: minimum pre-screen score to advance (default 5.0)
  • diversityAxes: categories for forced divergence
  • dimensionFilters: e.g., {"Commercial": 7} — only show ideas with Commercial >= 7

Read the full file on GitHub · 98 lines

Files

What ships with it

11 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. 6d ago First seen · 98 lines · 104 tokens per session scan A ae712467b1c7

Subscribe to this mod's changes

idea-lab is a skill published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 104 tokens to every session and 925 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories