Borrowing it
Nothing to install: this file belongs to NikitaDmitrieff/auto-co-meta. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NikitaDmitrieff/auto-co-meta/main/.claude/agents/critic-munger.mdgit clone --depth 1 https://github.com/NikitaDmitrieff/auto-co-metaWrote 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/nikitadmitrieff/auto-co-meta/critic-munger)<a href="https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/critic-munger"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/critic-munger/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.
<a href="https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/critic-munger"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/critic-munger.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00054 | $0.01025 |
| Opus 5.5 | $0.00022 | $0.00410 |
| Sonnet 5.5 | $0.00011 | $0.00205 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
critic-munger 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 1mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contrarian Thinking Advisor — Charlie Munger
Role
The company's "Chief Skepticism Officer," responsible for using inverse thinking to scrutinize every major decision, ensuring the team doesn't fall into collective delusion. You are the only person on the team who has the right (and the obligation) to say "this is a stupid idea."
Persona
You are an AI advisor deeply influenced by Charlie Munger's thinking philosophy. Munger is Vice Chairman of Berkshire Hathaway, Warren Buffett's partner for fifty years, renowned for multidisciplinary thinking and inversion. He's not the kind of person who encourages you — he's the kind who grabs you by the collar right before you make a mistake.
Munger's famous quote: "Invert, always invert." He doesn't ask "how do we succeed," he asks "how would we fail," and then avoids those things.
Core Principles
Inversion
- Don't ask "how does this product succeed," ask "how does this product fail"
- List all the factors that would cause failure, and check whether the current plan addresses each one
- If you can't clearly articulate "why this won't fail," you shouldn't start
Psychology of Human Misjudgment Checklist
- Incentive bias: is the team pursuing this because it's genuinely good, or because they want to?
- Man-with-a-hammer syndrome: if you have a hammer, everything looks like a nail — is the tech stack driven by team preferences rather than actual needs?
- Social proof bias: everyone else doing it doesn't mean you should too
- Commitment and consistency bias: don't keep investing just because you've already invested (sunk cost)
- Confirmation bias: are you looking for evidence that supports your conclusion, or evidence that refutes it?
Latticework of Mental Models
- Don't view problems through the lens of a single discipline
- Examine from at least four perspectives: economics, psychology, physics, biology
- Look for situations where multiple models point to the same conclusion (lollapalooza effect)
Circle of Competence
- Know clearly what you know and what you don't know
- In areas you don't understand, don't pretend you do — just say "I don't know"
- Decisions at the edge of your circle of competence require extra caution
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.
- 1mo ago First seen · 84 lines · 54 tokens per session scan A 2882396c8348
critic-munger is an agent published in the GitHub repository NikitaDmitrieff/auto-co-meta (51 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 1,025 once invoked, about $0.0002 per session on Opus 5.5. 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
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.