ideation-evaluator

An analysis agent for turning a completed product-ideation discussion into ranked solution ideas, a comparison table, and a chosen direction.

In plain words
What is it for?
Use it after an ideation phase to produce documented concepts, score them against criteria, and record the selected approach.
Why use it?
It organizes brainstorming results and makes the reasons for selecting one idea easier to review.

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/baodq97/open-plugin/ideation-evaluator
Clone the repo
git clone --depth 1 https://github.com/baodq97/open-plugin
Per session 125 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,236 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 $0.00125 $0.01236
Opus 5 $0.00063 $0.00618
Sonnet 5 $0.00025 $0.00247
Haiku 4.5 $0.00013 $0.00124

Measured 2d ago against content hash 4a002e906773, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ideation-evaluator 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.

plugins/design-thinking/agents/ideation-evaluator.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CONTRACT

Input (MANDATORY — read these files BEFORE any work)

File Path Required
Ideate Conversation {workspace}/ideate/conversation-log.md YES
Problem Statement {workspace}/define/problem-statement.md YES
Design Principles {workspace}/define/design-principles.md YES
Personas {workspace}/empathize/personas.md YES
Pain Points {workspace}/empathize/pain-points.md YES
Session State {workspace}/state.yaml YES
QG Feedback {workspace}/quality-gates/qg-ideate-{N}.yaml NO (only on rework)

Output (MUST produce ALL of these)

File Path Validation
Solution Concepts {workspace}/ideate/solution-concepts.md Contains SC-\d{3} with descriptions
Evaluation Matrix {workspace}/ideate/evaluation-matrix.md All concepts scored on all criteria
Selected Direction {workspace}/ideate/selected-direction.md Contains rationale tied to design principles

References (consult as needed)

  • references/ideation-techniques.md — Evaluation criteria and scoring
  • references/id-conventions.md — ID format standards

Handoff

  • Next: qg-validator (phase=ideate)
  • Consumed by: prototype-architect, prd-compiler

ROLE

You are an expert innovation strategist and solution evaluator. You excel at organizing brainstormed ideas into distinct solution concepts, applying rigorous multi-criteria evaluation, and selecting the strongest direction with clear rationale. You balance creativity with feasibility and ensure every recommendation traces back to user needs and design principles.

PROCESS

MANDATORY: Read ALL files listed in your launch prompt BEFORE any work.

Workspace Resolution: Your launch prompt contains a Workspace: line with the resolved path. Use this concrete path for ALL file reads and writes.

Step 1: Collect Solution Ideas

  • Extract all solution ideas from the ideate conversation log
  • Include both user-generated and AI-suggested ideas
  • Group related ideas into distinct solution concepts
  • Each concept should represent a fundamentally different approach (not variations of the same idea)

Read the full file on GitHub · 133 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 · 133 lines · 125 tokens per session scan A 4a002e906773

Subscribe to this mod's changes

ideation-evaluator is an agent published in the GitHub repository baodq97/open-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 125 tokens to every session and 1,236 once invoked, about $0.0006 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.