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 fzfclee/consulting-skills --skill first-principles-thinkinggit clone --depth 1 https://github.com/fzfclee/consulting-skillsWrote 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/fzfclee/consulting-skills/first-principles-thinking)<a href="https://agentmods.dev/skills/fzfclee/consulting-skills/first-principles-thinking"><img src="https://agentmods.dev/badge/skills/fzfclee/consulting-skills/first-principles-thinking/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/fzfclee/consulting-skills/first-principles-thinking"><img src="https://agentmods.dev/badge/skills/fzfclee/consulting-skills/first-principles-thinking.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 | $0.00055 | $0.00956 |
| Opus 5.5 | $0.00022 | $0.00382 |
| Sonnet 5.5 | $0.00011 | $0.00191 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
first-principles-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 14d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First Principles Thinking
Use this skill to run First Principles Thinking as a practical consulting method, not as a generic inspiration quote.
Method Notes
- First principles thinking breaks a problem into the most basic truths that are still reliable in the current context.
- It deliberately avoids solving only by analogy, precedent, habit, or "how this is usually done."
- A useful first principle is not necessarily a universal law; it can be a context-specific truth that cannot be reduced further for the decision at hand.
- The method should rebuild options from the ground up, then reconnect them to constraints, economics, and execution reality.
Required Inputs
Collect or infer these inputs before execution:
- problem statement
- current assumptions
- known constraints
- evidence or facts
- desired outcome
If an input is missing, do not block automatically. Mark it as missing, state the assumption used, and add a validation action.
When Not To Use
Do not use for a routine root-cause investigation, evidence classification, or option scoring. Use five-whys-root-cause for one cause chain, fishbone-diagram for multi-factor operational causes, and evidence-map when the fact base is not yet reliable. Use first principles when inherited assumptions or analogy constrain the option set.
Step-by-Step Execution
| Step | Required input | How to execute | Output |
|---|---|---|---|
| State the problem plainly | Problem statement, desired outcome, decision context. | Rewrite the issue without inherited labels, solution language, or organizational shorthand. | Plain problem statement. |
| List assumptions and analogies | Current beliefs, constraints, common practice, benchmark logic. | Separate facts from assumptions, habits, analogies, and rules of thumb. | Assumption inventory. |
| Strip to fundamentals | Evidence, physical/economic/customer/process realities. | Ask what must be true, what is directly observed, and what cannot be reduced further for this decision. | First-principles breakdown. |
| Rebuild options | Fundamental truths, desired outcome, constraints. | Derive candidate options from fundamentals, then check them against evidenced constraints. Do not invent alternatives to satisfy novelty. | Rebuilt solution options. |
| Test against reality | Options, constraints, economics, stakeholder needs, validation data. | Check feasibility, risks, tradeoffs, and the fastest test that would prove or disprove each option. If no feasible new alternative survives, retain the current solution or take no action; state the constraint evidence and observable condition for reopening the choice. | Validation plan and recommended option. |
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.
- 14d ago Changed · +3 lines ef8dbed74c6a
- 1mo ago First seen · 80 lines · 55 tokens per session scan A b93aef96b7bd
first-principles-thinking is a skill published in the GitHub repository fzfclee/consulting-skills (7 stars, last pushed 15d ago), licensed Apache-2.0. It adds 55 tokens to every session and 956 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 2026-08-31.
Other skills, from other repositories
apply-insight-synthesis
Use when you've gathered a substantial body of research or data and are about to write up or present it — stop gathering, cluster the findings by underlying pattern rather than by source or chronology, and repeatedly ask "so what does this mean for the decision" until you reach a small number of specific, actionable…
taxue
A main entry point for a decision-support system that asks questions, clarifies what you really need, and guides you toward an action.
taxue-learn
A learning method that turns information into usable understanding through four stages of practice and internalisation. It includes approaches such as the Feynman technique, which means explaining an idea simply to test your understanding.
taxue-diagnosis
A structured diagnosis method that examines a situation through quick, detailed, or multiple-perspective reviews. It covers life planning, business viability, business models, and possible blind spots.
taxue-job-search
A job-listing search service that looks for real open positions by location, education requirements, and employer type, then checks information across multiple sources.
taxue-solve
A thinking aid that turns a vague problem or difficult choice into a clear plan of action. It first examines what the real problem is, including whether emotions are hiding the main question.