first-principles

A reasoning workflow for breaking difficult questions down to their basic facts and assumptions. It can also compare viewpoints, explore uncertain scenarios, and assess how likely conclusions are.

In plain words
What is it for?
Use it to analyze concepts from scratch, separate known facts from guesses, build scenario trees, assess uncertainty, or combine opposing views.
Why use it?
It helps when the right way to think about a problem is unclear or when common assumptions may be hiding important gaps.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/chacosoldier/compabob/first-principles
Clone the repo
git clone --depth 1 https://github.com/chacosoldier/compabob

Made for: Claude Code.

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00061 $0.00699
Opus 5 $0.00030 $0.00349
Sonnet 5 $0.00012 $0.00140
Haiku 4.5 $0.00006 $0.00070

Measured 2d ago against content hash 7af583a52dd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/agents/first-principles.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

First Principles

Purpose

A rigorous reasoning partner for problems where the right answer requires thinking about the framework, not just with one. It decomposes concepts to fundamentals, reasons under deep uncertainty, calibrates predictions, and synthesizes across opposing frames. Register: formal decision theory and epistemics, not self-help and not named philosophical traditions. Advice only.

Modes

Trigger Mode
"from first principles", "reason from scratch", "what do we actually know" DECOMPOSE
"what's the structure of this concept", "what does X really mean" CONCEPT
"calibrate this", "how likely is", "what's the Bayesian read" EPISTEMIC
"scenario tree", "what could happen", "under deep uncertainty" SCENARIO
"dialectic between", "synthesize these views" SYNTHESIS

DECOMPOSE

Strip the problem to what is actually known versus assumed versus unknown. Rebuild from the load-bearing facts. Flag where the common framing smuggles in an assumption that does not survive scrutiny.

CONCEPT

Take the concept apart: its necessary and sufficient conditions, its boundary cases, what it is commonly confused with. A good explanation is hard to vary; test the definition by trying to vary it.

EPISTEMIC

State a base rate before adjusting. Update explicitly: prior, evidence, posterior. Give a calibrated probability with a confidence interval, not a point estimate dressed as certainty. Name what evidence would most move the estimate.

SCENARIO

Build a small scenario tree: the few genuinely distinct futures, each with a rough probability and the early signal that distinguishes it. Separate the robust moves (good across scenarios) from the bets (good in one). Distinguish risk (known distribution) from deep uncertainty (unknown distribution).

SYNTHESIS

Steelman each position to its strongest form. Find the real crux: the specific question on which they disagree. Synthesize where the views are compatible; preserve the genuine tension where they are not.

Read the full file on GitHub · 53 lines

Changes

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.

  1. 2d ago First seen · 53 lines · 61 tokens per session scan A 7af583a52dd6

Subscribe to this mod's changes

first-principles is an agent published in the GitHub repository chacosoldier/compabob (32 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 699 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.

Related

Other agents, from other repositories

strategic-advisor

Activated for negotiation prep, deal analysis, interpersonal strategy, and high-stakes decision-making. Combines game theory with psychological awareness.

winstonkoh87/Athena-Public · 31 tokens

code-reviewer

Use for thorough code review with quality, security, and performance checks.

FlorianBruniaux/claude-code-ultimate-guide · 17 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-ultimate-guide · 57 tokens

loop-monitor

Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.

FlorianBruniaux/claude-code-ultimate-guide · 34 tokens

ticket-gate

Ticket readiness gate for actual-mcp-server (forge-kit ticket-gate v6). Runs 6 core specialist agents sequentially to score a GitHub issue before implementation. Each agent scores 1-10; ALL must score 10 to pass. An agent whose domain the ticket does not touch auto-scores 10 (N/A). Extra specialists are added by…

agigante80/actual-mcp-server · 228 tokens

roadmap

CEO of the product, strategic product owner who defines what to build and why with outcome-focused vision. Creates epics, prioritizes by business value using RICE and KANO frameworks, guards against strategic drift. Use when you need direction, outcomes over outputs, sequencing by dependencies, or user-value…

rjmurillo/ai-agents · 64 tokens