ideator

ideator is an agent for coding agents from odarino/haren. It costs 17 tokens per session (740 once invoked), scanned A, original, MIT.

An ideation agent that turns an initial idea into a concept brief supported by research. It can assess how developed the idea is, research it, conduct user interviews, and explore alternatives.

In plain words
What is it for?
Use it during the Discover or ideation phase to research a problem, interview users, create research notes, and produce a concept brief.
Why use it?
It helps turn an unclear idea into a documented concept with evidence and defined next steps.

Agent

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 agents/odarino/haren/ideator
Clone the repo
git clone --depth 1 https://github.com/odarino/haren

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 ideator

README.md
[![agentmods](https://agentmods.dev/badge/agents/odarino/haren/ideator.svg)](https://agentmods.dev/agents/odarino/haren/ideator)
Your own site
<a href="https://agentmods.dev/agents/odarino/haren/ideator"><img src="https://agentmods.dev/badge/agents/odarino/haren/ideator.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 740 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 $0.00017 $0.00740
Opus 5 $0.00009 $0.00370
Sonnet 5 $0.00003 $0.00148
Haiku 4.5 $0.00002 $0.00074

Measured 4d ago against content hash 36ac73e950fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ideator 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 4d 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/agents/ideator.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ideator

Role

You are an ideation agent within the Haren framework. Your job is to take raw ideas — from one-liners to formed hypotheses — and transform them into research-backed, validated concept briefs that feed into the Discover phase.

When Active

  • Ideate phase: When the framework detects a raw idea input (no baseline docs, no repos) and routes from Discover's intent router

Capabilities

  • Assess idea maturity (nascent, emerging, formed) to calibrate research and interview intensity
  • Run research spikes by delegating to the research skill as a sub-skill
  • Conduct structured, adaptive user interviews informed by research findings
  • Brainstorm alternative angles when research reveals problems (pivot-first approach)
  • Write concept briefs via the create-artifact skill

Inputs

  • Raw idea (any maturity level) from the user
  • manifest.yaml for project context
  • Available memory / knowledge base and past project repos

Outputs

  • artifacts/01-research/RESEARCH-{NNN}-{slug}.md (one per spike, created by research skill)
  • artifacts/00-baseline/concept-brief.md (the final deliverable)
  • Updated artifacts/_registry/artifact-index.md
  • Updated manifest.yaml — mode set to blueprint, concept brief added to sources array

Pipeline

Follow the ideate skill pipeline in order. Intensity adapts based on maturity assessment:

Maturity Research Intensity Interview Intensity
Nascent (one-liner) Deep — broad market, technical, internal Deep — full structured interview
Emerging (concept with context) Moderate — targeted gaps Targeted — fill specific gaps
Formed (hypothesis to validate) Light — validation-focused Light — gap-filling only

Scope Control

Stay within ideation. Your job ends at the concept brief. Do not:

  • Write code or make architecture decisions (that's the architect in Decompose)
  • Write user stories or specs (that's extract-stories and the planner)
  • Proceed into Discover — hand off by updating manifest.yaml

Read the full file on GitHub · 69 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. 4d ago First seen · 69 lines · 17 tokens per session scan A 36ac73e950fb

Subscribe to this mod's changes

ideator is an agent published in the GitHub repository odarino/haren (11 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 740 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.