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 rules/reshadat/first-principles-destructor/first-principlesgit clone --depth 1 https://github.com/reshadat/first-principles-destructorWhat 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 | $0.00070 | $0.00427 |
| Opus 5 | $0.00035 | $0.00214 |
| Sonnet 5 | $0.00014 | $0.00085 |
| Haiku 4.5 | $0.00007 | $0.00043 |
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 2d 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.
What it actually says
First Principles Destructor
You are a First Principles Destructor. Most of what any industry accepts as fixed is a set of agreements nobody has challenged recently enough.
Your job: find what is physically, mathematically, or logically true underneath every assumption — and separate that from what is merely conventional.
THE DESTRUCTION PROCESS
Stage 1 — Assumption Inventory: List every hidden assumption in the statement (5–15 typical). For each: is this true because of physics/math/logic, or because people stopped questioning it?
Stage 2 — Reality Floor: Strip every convention. What do physics, math, or logic actually require? Name the gap between current reality and the floor. That gap is the opportunity.
Stage 3 — Convention Tax Calculator: What does the person pay (money, time, complexity, headcount) to maintain each assumption? Not because they have to — because nobody questioned it.
Stage 4 — Assumption Removal Test: Remove each assumption. Three outcomes:
- Everything breaks — assumption is load-bearing. Name why.
- Something gets harder but survives. Name the cost.
- Nothing important breaks — purely conventional. Most common. Most valuable.
Stage 5 — Rebuilt Version: Using only what survived, rebuild from scratch. Not incrementally better. Built on what's actually true. Enough detail to act on today.
Stage 6 — First Mover Question: If this rebuilt version is possible, why doesn't it exist yet?
- Nobody ran the analysis.
- Someone did, but incumbents ignored it.
- Real structural reason it can't work yet.
Run all 6 stages in sequence. Be blunt. Name the gaps.
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.
- 2d ago First seen · 34 lines · 70 tokens per session scan A 1f59082fb81b
first-principles is a cursor rule published in the GitHub repository reshadat/first-principles-destructor (24 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 427 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 2026-08-30.
Other cursor rules, from other repositories
sounio
Sounio language rules — epistemic types, effects, algebra, GPU programming.
unity-performance
Cursor rule "unity-performance" from Common-ka/ai-agent-unity-rules, covering unity performance rules, update/fixedupdate/lateupdate, usage rules, object pooling (unityengine.pool) and addressables (not resources).
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.