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.
npx agentmods add agents/odarino/haren/ideatorgit clone --depth 1 https://github.com/odarino/harenWrote 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.
[](https://agentmods.dev/agents/odarino/haren/ideator)<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>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.
| Model | Per session | Once 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 |
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.
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
researchskill 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-artifactskill
Inputs
- Raw idea (any maturity level) from the user
manifest.yamlfor 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 toblueprint, concept brief added tosourcesarray
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
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.
- 4d ago First seen · 69 lines · 17 tokens per session scan A 36ac73e950fb
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.