ideate

A product-idea generation stage that explores many possible solutions, then narrows them to a small number of bets with testable demand assumptions. The I-Framework is the larger process this stage belongs to.

In plain words
What is it for?
Use it after capturing user intent to generate candidate products, compare different approaches, choose one to three bets, and document them in Product/ideation.md.
Why use it?
It reduces the risk of settling on the first idea before considering alternatives or stating how demand will be tested.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/inscico/i-framework/ideate
Any agent
npx skills add InSciCo/i-framework --skill ideate
Clone the repo
git clone --depth 1 https://github.com/InSciCo/i-framework

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 630 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00059 $0.00630
Opus 5 $0.00030 $0.00315
Sonnet 5 $0.00012 $0.00126
Haiku 4.5 $0.00006 $0.00063

Measured 2d ago against content hash 0b4d68fac3eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ideate 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 2d 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/skills/ideate/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ideate — Stage 2: diverge, then converge

You retire solution & demand risk. First go wide (escape the first-idea trap), then narrow to a small number of bets with an explicit, testable demand hypothesis.

Procedure

1. Load context & check the gate (soft)

Read Product/intent.md. If it's missing, suggest /intent first. If its gate: open, warn that you're ideating on an unvalidated problem but proceed if the founder wants.

2. Diverge — fan out for breadth

Spawn a handful of subagents in parallel via the Task tool, each with a different lens, so the option space isn't anchored on one mindset. Suggested lenses (pick 4–6):

  • Cheapest MVP — the scrappiest thing that could work.
  • 10x technology — what becomes possible with the best available tech.
  • Different business model — subscription, marketplace, services, usage-based, free+data.
  • Adjacent analog — how an unrelated industry solved a structurally similar problem.
  • Do-it-for-them — a concierge/service version before any product.
  • Platform / ecosystem — enabling others to solve it.

Give each subagent the intent (problem, user, status quo) and ask for a short list of distinct candidate solutions with a one-line description each. Then dedupe and cluster the returned candidates yourself.

If the bet is tightly scoped or the user prefers, skip the fan-out and brainstorm a single broad pass inline.

3. Converge — score and narrow

Score each candidate on desirability (fit-to-intent / demand signal), feasibility, and differentiation potential (H/M/L). Narrow to 1–3 bets. Interview the founder to confirm the choice — their conviction and constraints matter as much as the scores.

4. Demand hypothesis & cheapest test

For the chosen bet(s), force a falsifiable demand hypothesis ("We believe will because ") and the smallest experiment that would confirm or kill it before building.

5. Write Product/ideation.md

Use the structure from the plugin's templates/ideation.md: the full option space (keep the killed ones and why), the chosen bet(s) and rationale, the demand hypothesis, and the cheapest test.

Read the full file on GitHub · 40 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. 2d ago First seen · 40 lines · 59 tokens per session scan A 0b4d68fac3eb

Subscribe to this mod's changes

ideate is a skill published in the GitHub repository InSciCo/i-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 630 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.