ideate

ideate is a skill for Claude Code, Codex from odarino/haren. It costs 20 tokens per session (1,643 once invoked), scanned A, original, MIT.

A workflow that turns an early product idea into a research-backed concept brief. It can use research, user interviews, and synthesis to clarify and test the idea before detailed planning.

In plain words
What is it for?
Use it when someone describes an idea or says they want to build something, especially before entering a project’s discovery or blueprint phase.
Why use it?
It helps replace a vague idea with a documented understanding of the problem, audience, and assumptions that need checking.

Skill for Claude CodeCodex

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

Good fit Use it when someone describes an idea or says they want to build something, especially before entering a project’s discovery or blueprint phase.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/odarino/haren/ideate
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 odarino/haren --skill ideate
Clone the repo
git clone --depth 1 https://github.com/odarino/haren

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 ideate

README.md
[![agentmods](https://agentmods.dev/badge/skills/odarino/haren/ideate.svg)](https://agentmods.dev/skills/odarino/haren/ideate)
Your own site
<a href="https://agentmods.dev/skills/odarino/haren/ideate"><img src="https://agentmods.dev/badge/skills/odarino/haren/ideate.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,643 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 $0.00020 $0.01643
Opus 5 $0.00010 $0.00822
Sonnet 5 $0.00004 $0.00329
Haiku 4.5 $0.00002 $0.00164

Measured 7d ago against content hash 07bfec3a144b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d 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.

content/skills/ideate/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ideate

Trigger: When the user presents a raw idea, concept, or "I want to build X" statement — read and follow this skill. Also read the agent definition at haren/agents/ideator.md.

Take a raw idea at any maturity level and transform it into a validated, research-backed concept brief. The concept brief becomes a baseline document for the Discover phase (blueprint mode).

When to Use

When the Discover intent router detects a raw idea input — no baseline docs, no repos, and the user provides a statement of intent. This skill is invoked automatically; users do not need to call it directly.

Pipeline

Six stages, always in order. Intensity adapts based on idea maturity.

Stage 1: Intake & Assessment

Accept the user's input and classify idea maturity:

  • Nascent: One-liner, vague idea, no context beyond the core concept
  • Emerging: Concept with some context — the user knows the problem, audience, or constraints
  • Formed: Hypothesis to validate — the user has a clear thesis and needs research to confirm or challenge it

Maturity determines intensity for Stages 2 and 3:

  • Nascent → deep research (broad), deep interview (full)
  • Emerging → moderate research (targeted gaps), targeted interview (specific gaps)
  • Formed → light research (validation-focused), light interview (gap-filling)

Output: Maturity classification with rationale, stored in working memory for later stages.

Stage 2: Research Spikes (automatic, parallel)

Resolve all required research IDs upfront using the resolve-next-id skill (call it once per spike, sequentially, before launching spikes in parallel).

Launch up to 3 research spikes by delegating to the research skill:

Spike Research Question Intensity Guide
Market "What is the market landscape for {idea}? Existing solutions, competitors, market size, trends, gaps." Nascent: broad survey. Emerging: targeted gaps. Formed: validation only.
Technical "What are the technical feasibility considerations for {idea}? Tech options, known pitfalls, prior art." Nascent: broad survey. Emerging: specific tech questions. Formed: validate chosen approach.
Internal "What relevant prior work, lessons, or reusable assets exist in our projects and memory for {idea}?" All levels: search memory / knowledge base, past project repos, git history.

Read the full file on GitHub · 151 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. 7d ago First seen · 151 lines · 20 tokens per session scan A 07bfec3a144b

Subscribe to this mod's changes

ideate is a skill published in the GitHub repository odarino/haren (11 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 1,643 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens