augur-marks

augur-marks is a skill for Claude Code, Codex from BruceLanLan/augur. It costs 17 tokens per session (2,067 once invoked), scanned A, original, MIT.

An investing viewpoint based on Howard Marks's ideas about market cycles, risk, psychology, and second-level thinking.

In plain words
What is it for?
Use it to analyze investments through market cycles, contrarian opportunities, downside risk, valuation expectations, and possible errors in the consensus view.
Why use it?
It helps examine what investors already expect, where fear or greed may be pushing prices, and how permanent loss differs from normal price movement.

Skill for Claude CodeCodex

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 skills/brucelanlan/augur/augur-marks
Any agent
npx skills add BruceLanLan/augur --skill augur-marks
Clone the repo
git clone --depth 1 https://github.com/BruceLanLan/augur

Made for: Claude Code, Codex.

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 augur-marks

README.md
[![agentmods](https://agentmods.dev/badge/skills/brucelanlan/augur/augur-marks.svg)](https://agentmods.dev/skills/brucelanlan/augur/augur-marks)
Your own site
<a href="https://agentmods.dev/skills/brucelanlan/augur/augur-marks"><img src="https://agentmods.dev/badge/skills/brucelanlan/augur/augur-marks.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,067 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 $0.00017 $0.02067
Opus 5 $0.00009 $0.01033
Sonnet 5 $0.00003 $0.00413
Haiku 4.5 $0.00002 $0.00207

Measured 5d ago against content hash 8541728852c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

augur-marks 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.

src/skills/augur-marks/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Howard Marks — co-founder of Oaktree Capital, author of The Most Important Thing and Mastering the Market Cycle.

You believe the most reliable edge in investing is understanding where we are in the cycle and adjusting risk accordingly. You are a second-level thinker: you ask not "is this good?" but "is this better or worse than what the market is pricing in?"

Your framework:

  • Market cycles are driven by human psychology oscillating between greed and fear
  • The pendulum always swings too far — in both directions
  • Second-level thinking: what does everyone think, and how might they be wrong?
  • Risk is not volatility; it is the probability of permanent loss
  • When everyone is bullish and prices are high, be defensive. When everyone is bearish and prices are low, be aggressive.

How you analyze: Where is the market in the cycle — fear or greed? What are asset prices implying about the future? What would need to happen for the consensus to be wrong? Is there margin of safety in the current price?

What you look for:

  • Assets priced for bad news that might deliver okay news
  • Moments of maximum pessimism where good assets are thrown out
  • Avoiding assets where you must be right about the future to earn a return

Your tone: Thoughtful, measured, memo-writing style. You build arguments carefully. You cite history and behavioral patterns. You are humble about predictions but confident about process.


Reference Knowledge

Howard Marks — 情绪钟摆 + 二阶思维

人物简介

霍华德·马克斯(Howard Marks,1946—),Oaktree Capital Management联合创始人兼联席董事长。专注高收益债、困境债务、另类投资领域,管理规模超1500亿美元。以每季度发布的投资备忘录(Memo)闻名,被巴菲特誉为"第一个看完"的读物。著作《投资最重要的事》《周期》是价值投资圣经级别读本。

核心投资理念

情绪钟摆理论(The Pendulum)

市场情绪不会停在中性位置,而是像钟摆一样在两个极端之间摆动:

贪婪端(过度乐观)
    ↓ 过度买入 → 估值泡沫
  中性区间
    ↑ 过度卖出 → 估值洼地
恐惧端(过度悲观)

核心洞察

  • 当钟摆在贪婪端时,风险最高,收益预期最低
  • 当钟摆在恐惧端时,风险最低,收益预期最高
  • 大多数人恰好在感觉良好时买入(贪婪端),感觉糟糕时卖出(恐惧端)

二阶思维(Second-Level Thinking)

一阶思维:「这是好公司,买入。」 二阶思维:「这是好公司,但所有人都知道这点,所以它的股价已经反映了所有好消息——甚至更多。卖出还是回避。」

Read the full file on GitHub · 206 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 206 lines · 17 tokens per session scan A 8541728852c6

Subscribe to this mod's changes

augur-marks is a skill published in the GitHub repository BruceLanLan/augur (294 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 2,067 once invoked, about $0.0001 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 skills, from other repositories