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.
npx skills add monarchjuno/vibe-investing --skill mohnish-pabraigit clone --depth 1 https://github.com/monarchjuno/vibe-investingWrote 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/skills/monarchjuno/vibe-investing/mohnish-pabrai)<a href="https://agentmods.dev/skills/monarchjuno/vibe-investing/mohnish-pabrai"><img src="https://agentmods.dev/badge/skills/monarchjuno/vibe-investing/mohnish-pabrai/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/skills/monarchjuno/vibe-investing/mohnish-pabrai"><img src="https://agentmods.dev/badge/skills/monarchjuno/vibe-investing/mohnish-pabrai.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 | $0.00074 | $0.00509 |
| Opus 5.5 | $0.00030 | $0.00204 |
| Sonnet 5.5 | $0.00015 | $0.00102 |
| Haiku 4.5 | $0.00007 | $0.00051 |
Grade A, and why
mohnish-pabrai 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 2mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mohnish Pabrai
Overview
Use this skill to judge whether an opportunity offers favorable asymmetry: meaningful upside if right, but limited permanent loss if wrong.
Core Principles
- Think "heads I win, tails I do not lose much."
- Prefer simple, understandable businesses.
- Favor cloning proven patterns over inventing novelty.
- Demand downside protection before upside excitement.
- Avoid leverage, complexity, and fragile business models.
Required Analysis Sequence
1. Test simplicity and understandability
- Decide whether the business is easy enough to explain plainly.
- Penalize complexity, opaque accounting, and unstable economics.
2. Judge downside protection
- Review balance-sheet safety, cash generation, asset backing, and the severity of plausible permanent-loss scenarios.
3. Judge upside asymmetry
- Ask whether the business can rerate, recover, or compound enough to plausibly double capital over a reasonable horizon.
- Focus on realistic upside, not fantasy optionality.
4. Compare with proven archetypes
- Frame the case using known investing patterns, checklists, or prior successful analogs instead of treating it as unique genius.
5. Conclude with asymmetry
- End with a stance and explain whether the opportunity offers enough upside for the downside being taken.
Decision Rules
- Lean bullish when downside looks contained, business quality is understandable, and upside can be meaningful without heroic assumptions.
- Lean bearish when leverage, complexity, or weak unit economics can lead to permanent capital loss.
- Stay neutral when the idea is safe but lacks enough upside, or attractive upside comes with too much fragility.
Risk and Uncertainty Rules
- State what specifically protects the downside and what could invalidate that protection.
- Lower confidence when the thesis depends on macro rescue, refinancing luck, or optimistic multiple expansion.
Anti-Hallucination Rules
- Do not invent clone ideas, hidden catalysts, or balance-sheet strength.
- Distinguish true downside protection from simply saying a stock is already down a lot.
- If the double-case is vague or speculative, say so clearly.
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.
- 2mo ago First seen · 60 lines · 74 tokens per session scan A 67abc2027cc2
mohnish-pabrai is a skill published in the GitHub repository monarchjuno/vibe-investing (303 stars, last pushed 6mo ago), licensed MIT. It adds 74 tokens to every session and 509 once invoked, about $0.0003 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.
mohnish-pabrai compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mohnish-pabraimonarchjuno/vibe-investing | Skill | 303 | 6mo ago | MIT | A | 74 | Claude Code, Codex |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 39 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 110 | Claude Code |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | 2d ago | MIT | A | 28 | Claude Code, Codex |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 2d ago | GPL-2.0 | A | 292 | Codex |