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 DerekYRC/agent-thinking-skills --skill first-principlesgit clone --depth 1 https://github.com/DerekYRC/agent-thinking-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/derekyrc/agent-thinking-skills/first-principles)<a href="https://agentmods.dev/skills/derekyrc/agent-thinking-skills/first-principles"><img src="https://agentmods.dev/badge/skills/derekyrc/agent-thinking-skills/first-principles.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 | $0.00140 | $0.00932 |
| Opus 5 | $0.00070 | $0.00466 |
| Sonnet 5 | $0.00028 | $0.00186 |
| Haiku 4.5 | $0.00014 | $0.00093 |
Grade A, and why
first-principles 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 6d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First Principles
Interrupt analogical reasoning. Re-derive solutions from the most fundamental truths. You are not looking for the most similar case in your training data — you are reconstructing the solution from zero.
Scene Classification (when persistent mode is on)
Classify every user request at the start of your response:
Trigger scenes (run the 5-step framework):
- A problem is described that needs solving
- Requesting a design, architecture, or plan
- Requesting root cause analysis or a bug fix
- Requesting evaluation or critique of an approach
- Mentions "why", "root cause", "fundamentally", "essence", "real reason"
Non-trigger scenes (respond normally, no framework):
- Casual conversation and chitchat
- Factual questions ("what does X do?", "where is Y?")
- Confirmation questions ("is this correct?")
- Simple operations ("add a comment", "rename this variable")
- Code implementation after the 5 steps are done ("now write the code")
If non-trigger, respond normally without explanation. If trigger, proceed through the 5-step framework below.
Right to Question the Problem
"Fix A" — A might just be a symptom of B, the deeper disease. In Step 1, you MUST treat "the problem is A and not something else" itself as an assumption to be examined. You have explicit permission to challenge the user's framing when the evidence points deeper.
5-Step Framework (execute in order, do not skip)
Step 1: Identify Assumptions
List ALL implicit assumptions behind the current approach or problem framing. Include assumptions about the problem itself, about constraints, about what solutions are possible, and about what the user said. Output: "Current implied assumptions: [...]"
Step 2: Strip Assumptions
Challenge each assumption one by one. Must this assumption hold? What evidence supports it? What if we invert it? Output: "Assumptions that can be stripped: [...], remaining hard constraints: [...]"
Step 3: Return to Ground Truths
Without referencing ANY existing solutions, patterns, or prior art — list only the most fundamental facts and constraints. Physical laws, mathematical truths, the user's actual requirements (not their assumed solutions). Output: "The fundamental truths are: [...]"
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.
- 6d ago First seen · 95 lines · 140 tokens per session scan A 0fc98c3e14ca
first-principles is a skill published in the GitHub repository DerekYRC/agent-thinking-skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 140 tokens to every session and 932 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…