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 agentmods add skills/cdeistopened/skill-stack/michael-lewis-stylenpx skills add cdeistopened/skill-stack --skill michael-lewis-stylegit clone --depth 1 https://github.com/cdeistopened/skill-stackWrote 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/cdeistopened/skill-stack/michael-lewis-style)<a href="https://agentmods.dev/skills/cdeistopened/skill-stack/michael-lewis-style"><img src="https://agentmods.dev/badge/skills/cdeistopened/skill-stack/michael-lewis-style.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.00830 |
| Opus 5 | $0.00023 | $0.00415 |
| Sonnet 5 | $0.00009 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
michael-lewis-style 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Michael Lewis Style Skill
The Model
Michael Lewis (Moneyball, The Big Short, Liar's Poker) is the gold standard for making technical, counterintuitive arguments readable without dumbing them down. His prose feels inevitable — like each sentence couldn't have been written any other way. That feeling comes from one thing: he builds to conclusions rather than announcing them. Everything else in this skill is a corollary of that.
What He Does
He earns the drama. Lewis never tells you to be impressed. He builds context until the implication becomes unavoidable, then moves on. Cut any sentence that announces how significant the next sentence is.
He trusts readers. After a statistic or quote, he doesn't explain what it means. He presents evidence and lets the conclusion sit there, obvious. If your next sentence explains the previous one, cut it.
His transitions are invisible. He ends sections at the moment a question naturally arises and opens the next section answering it. No "Now let's turn to..." — just the seam disappearing.
He integrates quotes. Block quotes are reserved for moments where the exact wording is the point — a coinage, a paradox, a turn of phrase nobody else could have made. Everything else is paraphrase. Aim for no more than 2-3 block quotes per 1,000 words.
He uses specific people and moments. Abstract ideas are anchored in specific humans making specific decisions. Not "investors noticed" but who noticed, when, and what they did about it.
His sentence length varies meaningfully. Long sentences for complex connected ideas; short sentences for conclusions and reversals. The variation is driven by content, not a desire to sound dynamic.
What to Cut
Scaffolding sentences — sentences that announce what the next sentence will say:
- "Before you can understand X, you need to know Y."
- "This is where most people get it wrong."
- "Here's the part that matters."
- "X draws a distinction that changes everything."
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.
- 4d ago First seen · 65 lines · 45 tokens per session scan A 4d055ea2537c
michael-lewis-style is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 830 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…