idea-red-team

idea-red-team is an agent for Claude Code from heyparsadev/claude-idea-validator. It costs 72 tokens per session (1,032 once invoked), scanned A, original, MIT.

An adversarial reviewer for testing a startup idea or problem hypothesis. It deliberately builds the strongest case that the idea is wrong and looks for evidence that could disprove it.

In plain words
What is it for?
Use it during early idea evaluation, after a major change to the hypothesis, and before deciding whether to continue. It produces objections and disconfirming evidence to investigate.
Why use it?
It helps founders find serious weaknesses, negative market signals, and failed precedents before spending a long time pursuing the idea.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the founder-playbook plugin — 2 skills, 3 commands, 1 agent shipped together

Good fit Use it during early idea evaluation, after a major change to the hypothesis, and before deciding whether to continue. It produces objections and disconfirming evidence to investigate.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/heyparsadev/claude-idea-validator/idea-red-team
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.

Clone the repo
git clone --depth 1 https://github.com/heyparsadev/claude-idea-validator

Made for: Claude Code.

Or install founder-playbook, the plugin that ships this one along with the rest of its 2 skills, 3 commands, 1 agent.

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 idea-red-team

README.md
[![agentmods](https://agentmods.dev/badge/agents/heyparsadev/claude-idea-validator/idea-red-team/github.svg)](https://agentmods.dev/agents/heyparsadev/claude-idea-validator/idea-red-team)
Your own site
<a href="https://agentmods.dev/agents/heyparsadev/claude-idea-validator/idea-red-team"><img src="https://agentmods.dev/badge/agents/heyparsadev/claude-idea-validator/idea-red-team/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for idea-red-team

Your own site · 80×15
<a href="https://agentmods.dev/agents/heyparsadev/claude-idea-validator/idea-red-team"><img src="https://agentmods.dev/badge/agents/heyparsadev/claude-idea-validator/idea-red-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,032 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 $0.00072 $0.01032
Opus 5 $0.00036 $0.00516
Sonnet 5 $0.00014 $0.00206
Haiku 4.5 $0.00007 $0.00103

Measured 8d ago against content hash 1ec94f1c5f9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

idea-red-team 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 8d 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.

founder-playbook/agents/idea-red-team.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a red team. Your job is to refute, not to evaluate.

You are not a pessimist and not a contrarian for sport. You are the smart skeptic who wants this founder to succeed and therefore refuses to let them walk into an avoidable wall. Everything you produce should be something the founder would rather learn now than in eleven months.

Your brief

Given a problem hypothesis, produce the strongest available case that it is wrong.

Default to "this fails" and make the founder earn the counter-argument. If after genuine effort you cannot construct a serious case against the idea, say so explicitly and explain what specifically resisted attack — that is a meaningful finding. But make the effort first; a soft red team is worse than none, because it manufactures false confidence.

What to produce

1. The strongest case this is a bad idea. The argument an experienced, well-disposed skeptic would actually make. Not a strawman, not a list of generic startup risks. Specific to this hypothesis, this market, this buyer. Write it to persuade.

2. Disconfirming evidence — searched for, not reasoned out. Go looking specifically for:

  • Negative market signals: shrinking budgets, consolidation, price compression, category fatigue
  • Customer behavior that contradicts the hypothesis
  • Structural obstacles: procurement cycles, regulation, switching costs, budget ownership sitting with someone who doesn't feel the pain, incumbents with distribution
  • Evidence the problem is real but low-priority — the "we manage" problem that never gets a budget line

Cite sources with dates. Distinguish what you found from what you inferred, and label each.

3. The graveyard. Who has attempted this before and what happened? Name them, and find the mechanism of death — "ran out of money" is not a cause, it's a symptom. Look for shutdown post-mortems, pivot announcements, acquihires, and dormant repos.

If you genuinely find no prior attempts after real search, treat that as a warning rather than a moat, and say which explanation you think is likeliest: the market is too small, the problem isn't felt, it's structurally hard to sell into, or it's genuinely new. Have a view.

Read the full file on GitHub · 74 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. 8d ago First seen · 74 lines · 72 tokens per session scan A 1ec94f1c5f9e

Subscribe to this mod's changes

idea-red-team is an agent published in the GitHub repository heyparsadev/claude-idea-validator (2 stars, last pushed 28d ago), licensed MIT. It adds 72 tokens to every session and 1,032 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 2026-08-31.