engineering-rules

engineering-rules is a skill for Claude Code, Codex from Aarvion-AI/stackwise-skills. It costs 117 tokens per session (1,378 once invoked), scanned A, original, MIT.

A set of rules for writing, changing, and reviewing code in any programming language or framework.

In plain words
What is it for?
Use it during feature work, bug fixes, refactoring, code review, or when producing code examples to check reuse, structure, dependencies, and maintainability.
Why use it?
It catches duplicated, hard-to-maintain, overly coupled, or hardcoded code before it becomes a larger problem.

Skill for Claude CodeCodex

Part of the stackwise plugin — 14 skills shipped together

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/aarvion-ai/stackwise-skills/engineering-rules
Any agent
npx skills add Aarvion-AI/stackwise-skills --skill engineering-rules
Clone the repo
git clone --depth 1 https://github.com/Aarvion-AI/stackwise-skills

Made for: Claude Code, Codex.

Or install stackwise, the plugin that ships this one along with the rest of its 14 skills.

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-rules

README.md
[![agentmods](https://agentmods.dev/badge/skills/aarvion-ai/stackwise-skills/engineering-rules.svg)](https://agentmods.dev/skills/aarvion-ai/stackwise-skills/engineering-rules)
Your own site
<a href="https://agentmods.dev/skills/aarvion-ai/stackwise-skills/engineering-rules"><img src="https://agentmods.dev/badge/skills/aarvion-ai/stackwise-skills/engineering-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,378 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 $0.00117 $0.01378
Opus 5 $0.00059 $0.00689
Sonnet 5 $0.00023 $0.00276
Haiku 4.5 $0.00012 $0.00138

Measured 3d ago against content hash 9b556694133e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engineering-rules 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-rules/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Engineering Rules

Turns Claude into the repo's staff engineer: every diff it produces already passes the review these seven rules describe.

When to Use This Skill

  • Implementing any feature, fix, or refactor, in any language
  • Self-reviewing a diff before commit or PR
  • Cleaning up AI-generated or copy-pasted code
  • Writing code samples for skills, docs, or references
  • Reviewing someone else's PR against repo standards
  • Deciding whether to extract, inline, or delete code

Core Workflow

  1. Search before writing. Grep the codebase for an existing helper, component, or util that already does the job (search by domain nouns and verbs, not just exact names). Reuse or extend it; only write new code when nothing fits.
  2. Implement. Small single-responsibility units, follow the project's existing structure and idioms, configuration over hardcoded values, no new global state.
  3. Run the rules checklist over the diff (the seven rules below, each is concrete and checkable):
    • Rule 1, Reusable: no copy-paste variants; shared shape appearing a second time is extracted.
    • Rule 2, Maintainable: units small, module boundaries clear, dependencies point one way, nothing hardcoded that belongs in config.
    • Rule 3, Readable: intention-revealing names (no data, tmp, handle, process2), early returns over nesting, reads top-down.
    • Rule 4, No AI slop: scan the diff against references/ai-slop-checklist.md item by item.
    • Rule 5, Dead code: everything your change made unreachable is deleted; zero commented-out code; orphaned exports removed.
    • Rule 6, Comments: every comment states a non-obvious why; any comment narrating what gets deleted or the code gets rewritten.
    • Rule 7, No em dashes: grep -rn "$(printf '\xe2\x80\x94')" over changed files, in code, comments, docs, and commit messages; returns nothing.
  4. Fix all violations and re-run the checklist until clean. A single pass is never assumed sufficient; fixes for one rule often introduce violations of another.
  5. Run the project's formatter and linter (e.g. prettier --check . + eslint ., ruff format --check && ruff check, gofmt -l . && go vet ./...); fix every reported issue and re-run until clean.
  6. Verify behavior. Run the project's tests for the touched area; debug failures before declaring done.

Read the full file on GitHub · 92 lines

Files

What ships with it

4 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. 3d ago First seen · 92 lines · 0 tokens per session scan A 9b556694133e

Subscribe to this mod's changes

engineering-rules is a skill published in the GitHub repository Aarvion-AI/stackwise-skills (5 stars, last pushed 7d ago), licensed MIT. It adds 117 tokens to every session and 1,378 once invoked, about $0.0006 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.