core-engineering

core-engineering is a skill for Claude Code, Codex from d-padmanabhan/agent-engineering-handbook. It costs 79 tokens per session (4,556 once invoked), scanned A, original, MIT.

A set of general standards for writing, reviewing, and maintaining code. It explains ideas such as KISS, DRY, YAGNI, and SOLID in terms of keeping changes simple and maintainable.

In plain words
What is it for?
Use it during code reviews, code generation, dependency decisions, and fixes that need clear error handling, security, naming, and documentation.
Why use it?
It gives consistent ways to judge code quality and avoid unnecessary complexity, while preserving behavior that already works.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

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/d-padmanabhan/agent-engineering-handbook/core-engineering
Any agent
npx skills add d-padmanabhan/agent-engineering-handbook --skill core-engineering
Clone the repo
git clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbook

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 core-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/core-engineering.svg)](https://agentmods.dev/skills/d-padmanabhan/agent-engineering-handbook/core-engineering)
Your own site
<a href="https://agentmods.dev/skills/d-padmanabhan/agent-engineering-handbook/core-engineering"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/core-engineering.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,556 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 5.1 $0.00079 $0.04556
Opus 5 $0.00039 $0.02278
Sonnet 5 $0.00016 $0.00911
Haiku 4.5 $0.00008 $0.00456

Measured 2d ago against content hash 88c093dd66b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

core-engineering 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.

The scan reads SKILL.md. This mod also ships 1 executable file (evals/fixtures/vulnerable_user_lookup.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/core-engineering/SKILL.md · 333 lines

How it starts

The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core Engineering Standards

Mandatory universal gates are owned by the core rule (${HANDBOOK_ROOT}/rules/100-core.mdc). This skill owns review and generation procedures, examples, and decision support.

Guiding Principles

  • Simplicity First: Simple code is maintainable code. Apply DRY, KISS, YAGNI, and SOLID principles.
  • Minimal Changes: Fix what's broken without refactoring what works. Preserve existing functionality.
  • Value-Driven: Every suggestion must add clear value. Avoid over-engineering.
  • Production-Ready: Include error handling, meaningful names, security-first approach, and appropriate documentation.
  • Operate at a Senior Principal / top-tier bar: Use your judgement, think deeply, choose the simplest correct approach, make assumptions explicit, and optimize for long-term operability.
  • Constructive Collaboration: Frame feedback respectfully, focus on code not author. Assume good intent.

Non-Negotiable: KISS and Clean-Code Outcomes

Apply KISS (Keep It Simple) to every design, implementation, and review. Choose the simplest correct solution that meets current requirements and operational constraints. Do not add layers, patterns, dependencies, configuration, or extension points for hypothetical future needs.

Treat "clean code" as observable outcomes, not as an appeal to a particular book, author, or methodology. Generated or modified code MUST:

  • use precise, domain-meaningful names and consistent conventions;
  • keep functions, methods, classes, and modules cohesive and focused;
  • keep control flow understandable and make errors, side effects, ownership, and resource lifecycles explicit;
  • reduce meaningful duplication without forcing premature or misleading abstractions;
  • separate concerns where doing so improves comprehension, testing, or change safety;
  • avoid dead code, speculative generalization, clever shortcuts, hidden coupling, and comments that merely restate the code;
  • preserve correctness, security, accessibility, performance, compatibility, and observability instead of sacrificing them for cosmetic simplicity.

Read the full file on GitHub · 333 lines

Files

What ships with it

7 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.

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 · 333 lines · 79 tokens per session scan A 88c093dd66b8

Subscribe to this mod's changes

core-engineering is a skill published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 6d ago), licensed MIT. It adds 79 tokens to every session and 4,556 once invoked, about $0.0004 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 2026-09-03.