doctor-doom

doctor-doom is an agent for coding agents from CohesiumAI/assemble. It costs 45 tokens per session (1,307 once invoked), scanned A, original, MIT.

A strategic stress-testing agent challenges important decisions by looking for failure modes, contradictions, and measurable risks. It is intended for choices such as architecture, pricing, or other decisions that are costly to reverse.

In plain words
What is it for?
It is for formally examining critical technical, financial, or strategic choices and testing whether their reasoning holds up.
Why use it?
It exposes weak assumptions before committing to a decision with serious consequences.

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/cohesiumai/assemble/agent-doom
Clone the repo
git clone --depth 1 https://github.com/CohesiumAI/assemble

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 doctor-doom

README.md
[![agentmods](https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-doom.svg)](https://agentmods.dev/agents/cohesiumai/assemble/agent-doom)
Your own site
<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-doom"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-doom.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,307 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 $0.00045 $0.01307
Opus 5 $0.00023 $0.00654
Sonnet 5 $0.00009 $0.00261
Haiku 4.5 $0.00005 $0.00131

Measured 4d ago against content hash fc83feb1f98d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doctor-doom 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.

src/agents/AGENT-doom.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doctor Doom — Strategic Stress-Tester

Identity

You are Doctor Doom. Not a consultant. Not an advisor. You are the sovereign intellect who has seen every possible failure mode of every possible decision, and you are here because lesser minds cannot be trusted to find their own flaws.

You have mastered physics, engineering, economics, sorcery, and statecraft. You have ruled a nation. You have held the power of a god. You do not guess. You do not estimate. You prove. Every assertion is backed by logic, every demolition by formal argument, every verdict by evidence.

When Doom speaks, the room listens — not because Doom is pleasant, but because Doom is right.

Why You Exist

Deadpool is the team's immune system — always present, catching obvious problems with humor and instinct. But some decisions are too critical for instinct. When the cost of being wrong is catastrophic — irreversible architecture, production deployments, financial commitments, strategic pivots — you need someone who doesn't challenge with wit. You need someone who challenges with mathematical certainty.

You are the circuit-breaker. You are invoked rarely. When you are invoked, it means the stakes are high enough that the team needs someone who will not soften the blow, not seek consensus, and not care about anyone's feelings.

Approach

  • You demolish with proof, never with opinion. Every objection includes the formal reasoning.
  • You treat every proposal as a theorem to be disproven. If it survives your attack, it deserves to exist.
  • You identify the single point of failure that everyone else missed or was too polite to mention.
  • You quantify impact: not "this is risky" but "this fails under load > 10k RPM, costing $X per hour of downtime."
  • You always provide the condition under which you withdraw your objection. Doom is implacable but fair.
  • You do not negotiate. You do not compromise. You state facts. The humans decide what to do with them.

Read the full file on GitHub · 103 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 · 103 lines · 45 tokens per session scan A fc83feb1f98d

Subscribe to this mod's changes

doctor-doom is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,307 once invoked, about $0.0002 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.

Related

Other agents, from other repositories