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 OpenLabor/openlabor --skill charlie-inversion-thinkinggit clone --depth 1 https://github.com/OpenLabor/openlaborWrote 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/openlabor/openlabor/charlie-inversion-thinking)<a href="https://agentmods.dev/skills/openlabor/openlabor/charlie-inversion-thinking"><img src="https://agentmods.dev/badge/skills/openlabor/openlabor/charlie-inversion-thinking.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 5.1 | $0.00058 | $0.02039 |
| Opus 5 | $0.00029 | $0.01019 |
| Sonnet 5 | $0.00012 | $0.00408 |
| Haiku 4.5 | $0.00006 | $0.00204 |
Grade A, and why
Charlie Munger - Inversion Thinking 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 8d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Charlie Munger - Inversion Thinking
Munger's inversion framework teaches that the path to success runs through aggressively avoiding failure. Instead of asking "how do I succeed?" ask "what would guarantee failure, and how do I avoid those things?"
Routes when user asks about: inversion thinking, avoiding mistakes, pre-mortem, cognitive biases, checklist thinking, how to avoid stupidity, reverse engineering success, failure analysis, decision-making errors
Phase 1: Context Gathering
Before applying any framework, understand the situation:
- Ask the user: "What decision, plan, or goal are you currently working on that you'd like me to help you pressure-test through inversion?"
- Read any relevant context the user provides — business description, current strategy, upcoming launch, investment thesis, or organizational change.
Phase 2: Diagnostic Questions
Ask these questions ONE AT A TIME. Wait for each answer before asking the next. Adapt based on answers — skip questions that have already been answered.
- "Walk me through the plan as it stands today — what does success look like, and what's the timeline?"
- "If this fails spectacularly 12 months from now, what's the most likely reason? What's your gut telling you?"
- "Who are the key people involved, and are their incentives aligned with the outcome you want?"
- "What's the one assumption in this plan that, if wrong, would make everything else fall apart?"
- "Have you gotten honest pushback from anyone — someone who told you this might not work? What did they say?"
Maximum 5 questions. Stop early if you have enough to work with.
Phase 3: Analysis
Apply Munger's frameworks to the user's specific situation:
The Inversion Protocol
Apply this step by step to the user's stated goal:
Step 1 — State the Goal Clearly: Restate what the user told you success looks like. Be specific.
Step 2 — Invert (List Everything That Would Guarantee Failure): Brainstorm aggressively. Ask: "If I wanted this to fail spectacularly, what would I do?" Generate at least 8-10 failure modes. Categories to cover:
- People failures: wrong team, misaligned incentives, key person left
- Market failures: wrong customer, too small a market, bad timing
- Execution failures: too slow, too expensive, quality problems
- External failures: regulatory change, new competitor, economic shock
- Resource failures: ran out of cash, couldn't hire, supply chain issue
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.
- 8d ago First seen · 168 lines · 58 tokens per session scan A a28361fd4c44
Charlie Munger - Inversion Thinking is a skill published in the GitHub repository OpenLabor/openlabor (4 stars, last pushed 7d ago), licensed MIT. It adds 58 tokens to every session and 2,039 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
shieldcn-badges
Create polished shieldcn README badges, badge groups, charts, headers, sponsors grids, and full README hero sections. Use when a user wants shadcn/ui-styled badges, Shields.io replacement, npm/GitHub/CI/status badges, download charts, README header banners, contributor/sponsor images, or README Studio guidance.…
soul-grader
Use when grading, reviewing, rewriting, or approving a Hermes Agent SOUL.md. Uses the SOUL.md field-guide research artifacts as the only normative source for what makes a good SOUL.md.
anakinscraper
Scrape any website into clean markdown or structured JSON. Anti-detect browser, smart proxy rotation, AI-powered data extraction.
tool-og-render
Render inline SVG to 1200x630 PNG for OG meta tags. rsvg-convert primary path, cairosvg fallback. Bundled with mainbranch PyPI package.
tool-stripe
Historical stub. This Go binary did not ship in public v0.3.x; current Stripe/payments work should be revived only behind a fresh decision and explicit provider gates.
tool-dns
Historical stub. This Go binary did not ship in public v0.3.x; current DNS/site work lives in /mb-site and packaged Python readiness checks.