evaluate-idea

evaluate-idea is a command for coding agents from TobiasBlask/open-paper-machine. It costs 84 tokens per session (344 once invoked), scanned A, original, MIT.

A structured review of a research idea before substantial time is invested in it. It examines novelty, impact, timing, feasibility, competition, clarity, and the potential for a strong research story.

In plain words
What is it for?
Running a six-stage idea review with specialist perspectives and saving a PURSUE, PARK, or KILL decision with next steps.
Why use it?
It helps distinguish ideas worth pursuing from ideas that need changes or should be set aside before months of work begin.

Command

Part of the open-academic-paper-machine plugin — 33 skills, 21 commands, 4 agents shipped together

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 commands/tobiasblask/open-paper-machine/evaluate-idea
Clone the repo
git clone --depth 1 https://github.com/TobiasBlask/open-paper-machine

Or install open-academic-paper-machine, the plugin that ships this one along with the rest of its 33 skills, 21 commands, 4 agents.

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 evaluate-idea

README.md
[![agentmods](https://agentmods.dev/badge/commands/tobiasblask/open-paper-machine/evaluate-idea.svg)](https://agentmods.dev/commands/tobiasblask/open-paper-machine/evaluate-idea)
Your own site
<a href="https://agentmods.dev/commands/tobiasblask/open-paper-machine/evaluate-idea"><img src="https://agentmods.dev/badge/commands/tobiasblask/open-paper-machine/evaluate-idea.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 344 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 $0.00084 $0.00344
Opus 5 $0.00042 $0.00172
Sonnet 5 $0.00017 $0.00069
Haiku 4.5 $0.00008 $0.00034

Measured 5d ago against content hash d47de697f049, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluate-idea 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 5d 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.

commands/evaluate-idea.md · 37 lines

What it actually says

/evaluate-idea — Research Idea Stress-Test

Read skills/idea-engine/SKILL.md and execute the full 6-phase idea evaluation pipeline.

The user provides a research idea, topic, or question. Run the complete evaluation: Phase 1 (SEED) → Phase 2 (DIVERGE) → Phase 3 (EVALUATE) → Phase 4 (DEEPEN) → Phase 5 (FRAME) → Phase 6 (DECIDE).

Save the evaluation to research-evaluations/YYYY-MM-DD-<topic-slug>.md.

If the verdict is PURSUE and the user wants to proceed, hand off to the paper machine pipeline (Phase 1: Reconnaissance).

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. 5d ago First seen · 37 lines · 84 tokens per session scan A d47de697f049

Subscribe to this mod's changes

evaluate-idea is a command published in the GitHub repository TobiasBlask/open-paper-machine (18 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 344 once invoked, about $0.0004 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.