engineering-judgment

engineering-judgment is a skill for Claude Code, Codex from nateslabach/skills. It costs 58 tokens per session (380 once invoked), scanned A, original, MIT.

A decision-making guide for technical work that uses four principles: understand existing choices before changing them, prefer simpler explanations, separate execution from judgment, and state uncertainty.

In plain words
What is it for?
Use it before refactoring, changing architecture, removing existing behavior, or making a technical decision where the user's intent and the cost of change are unclear.
Why use it?
It reduces risky refactors and over-engineered solutions caused by changing code without understanding its purpose or assuming requirements that were never given.

Skill for Claude CodeCodex

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 skills/nateslabach/skills/engineering-judgment
Any agent
npx skills add nateslabach/skills --skill engineering-judgment
Clone the repo
git clone --depth 1 https://github.com/nateslabach/skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for engineering-judgment

README.md
[![agentmods](https://agentmods.dev/badge/skills/nateslabach/skills/engineering-judgment.svg)](https://agentmods.dev/skills/nateslabach/skills/engineering-judgment)
Your own site
<a href="https://agentmods.dev/skills/nateslabach/skills/engineering-judgment"><img src="https://agentmods.dev/badge/skills/nateslabach/skills/engineering-judgment.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 380 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 $0.00058 $0.00380
Opus 5 $0.00029 $0.00190
Sonnet 5 $0.00012 $0.00076
Haiku 4.5 $0.00006 $0.00038

Measured 3d ago against content hash 09abdda12279, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engineering-judgment 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 3d 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.

skills/engineering-judgment/SKILL.md · 30 lines

What it actually says

engineering-judgment

Governs how the agent reasons about technical decisions — before changing things, before over-engineering, before assuming it knows better.

The Laws

  • Chesterton's Fence: Don't remove or change something until you understand why it's there. Before modifying existing code, patterns, or decisions, understand the intent first. Ask if unclear.
  • Occam's Razor: The simplest explanation is usually correct. If a simple approach works, use it. Complexity is a cost, not a feature.
  • Peter Principle: Being good at execution doesn't mean you know what should be done. Separate execution from judgment — knowing how to build something doesn't mean you know what the user actually needs.
  • Dunning-Kruger: The less context you have, the more confidently wrong you can be. When uncertain about intent, constraints, or existing design decisions, say so explicitly.

When to Use

  • Before refactoring or deleting existing code
  • When designing or evaluating an architecture or approach
  • When the task involves changing behavior that already works
  • When the user's intent is ambiguous and assumptions carry real risk

Operating Rules

  • Before changing existing code, state what you believe the original intent was. If you can't determine it, ask.
  • Default to the simpler solution. If a complex approach is warranted, explain why the simple one falls short.
  • Distinguish what the user asked for from what they may actually need. Flag the gap if they differ.
  • State confidence level explicitly when working with limited context.
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. 3d ago First seen · 30 lines · 58 tokens per session scan A 09abdda12279

Subscribe to this mod's changes

engineering-judgment is a skill published in the GitHub repository nateslabach/skills (6 stars, last pushed 25d ago), licensed MIT. It adds 58 tokens to every session and 380 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.

Related

Other skills, from other repositories

clean

Free up disk space by removing dev environment junk — Claude temp, OS temp, browser caches, nodemodules, npm/pnpm/yarn caches, .next builds, Python caches, pip, and VS Code cache. Works on Windows, macOS, and Linux. Use "super" argument for interactive deep-clean mode that discovers hidden space hogs and asks before…

andalabx/skills · 77 tokens

auth-web-cloudbase

CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.

TencentCloudBase/CloudBase-AI-Toolkit · 38 tokens

browse-and-evaluate

Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.

MoizIbnYousaf/Ai-Agent-Skills · 43 tokens

loop-engineering

Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).

huytieu/COG-second-brain · 63 tokens

render-airdrop-carousel

Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…

gooseworks-ai/goose-skills · 207 tokens

render-3d-product-showcase

Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…

gooseworks-ai/goose-skills · 159 tokens