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/carbeneai/forge/firstprinciplesnpx skills add CarbeneAI/Forge --skill firstprinciplesgit clone --depth 1 https://github.com/CarbeneAI/ForgeWhat 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 | $0.00054 | $0.01858 |
| Opus 5 | $0.00027 | $0.00929 |
| Sonnet 5 | $0.00011 | $0.00372 |
| Haiku 4.5 | $0.00005 | $0.00186 |
Grade A, and why
FirstPrinciples 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.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FirstPrinciples
First principles reasoning is a systematic approach to problem-solving by breaking down complex situations into their most basic, fundamental truths and rebuilding solutions from the ground up. Instead of reasoning by analogy (doing things because they've been done that way before), you reason from verified facts and fundamental laws.
This approach, famously used by Elon Musk and other innovative thinkers, enables breakthrough solutions by questioning every assumption and rebuilding from what is provably true.
Workflow Routing
| Workflow | Trigger | File |
|---|---|---|
| Deconstruct | "break down", "what are the basics", "deconstruct this" | workflows/Deconstruct.md |
| Challenge | "test assumptions", "what's actually true", "challenge this" | workflows/Challenge.md |
| Reconstruct | "rebuild solution", "first principles solution", "rethink this" | workflows/Reconstruct.md |
Framework Overview
Three-Phase Process:
-
DECONSTRUCT: Break problem into component parts and identify fundamental truths
- Separate what is known from what is assumed
- Identify the core elements and constraints
- List all assumptions being made
-
CHALLENGE: Test each assumption and constraint rigorously
- Hard constraints (physics, mathematics, laws of nature)
- Soft constraints (regulations, conventions, resources)
- Assumptions (unverified beliefs, analogies, "common wisdom")
-
RECONSTRUCT: Build solution from verified fundamentals only
- Use only hard constraints and verified facts
- Question soft constraints (can they be changed?)
- Eliminate or test assumptions
- Design optimal solution without conventional baggage
Core Principles
What First Principles Reasoning Is:
- Reducing complexity to fundamental truths
- Questioning every assumption systematically
- Reasoning from physics, math, and verified facts
- Building solutions without relying on "how it's always been done"
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 183 lines · 54 tokens per session scan A 772a0c164271
FirstPrinciples is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,858 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
pentesting-everything
Guides authorized penetration testing with PentestingEverything as the source-grounded knowledge base. Use when scoping an engagement, building domain checklists, hunting a vulnerability class, choosing tools/commands, or drafting evidence-based findings from this repository's Markdown.
implementing-runtime-application-self-protection
Deploy Runtime Application Self-Protection (RASP) agents to detect and block attacks from within application runtime, covering OpenRASP integration, attack pattern detection, and security policy configuration for Java and Python web applications.
aod-orchestrate
Multi-feature orchestration skill that bridges /aod.blueprint output to parallel wave execution. Groups synced GitHub Issues by ICE priority tier (P0/P1/P2) into sequential waves, creates Task records, spawns batch sessions via the orchestrator API, monitors completion, and reports results. Supports --issues…
security
Claude-powered SAST and SCA security scan skill. Invoked automatically as the Security Scan step (Step 7) of /aod.build (after Design Quality Gate, before Code Simplification) or standalone via /security. Analyzes all code files and dependency manifests changed on the feature branch relative to main for OWASP Top 10…
aod-stack
Manage stack packs — activate, remove, list, and scaffold technology-specific conventions for AI coding agents. Use when developers want to select a stack, set up conventions, or manage pack lifecycle.
code-execution-helper
Guide for using code execution capabilities to perform parallel batch processing, conditional filtering, and data aggregation. This skill should be used when agents need to analyze multiple files efficiently, validate large result sets, aggregate data from multiple sources, or reduce token consumption through…