naming

naming is a skill for Claude Code, Codex from tslateman/duet. It costs 55 tokens per session (1,620 once invoked), scanned A, original, MIT.

A code-review skill for choosing names that clearly describe what code represents and does. It treats naming problems as possible signs of unclear design or mixed responsibilities.

In plain words
What is it for?
Use it when naming or renaming code, reviewing names, or investigating unclear abstractions during code review.
Why use it?
It helps prevent vague, misleading, inconsistent, or confusing names that make code harder to understand and maintain.

Skill for Claude CodeCodex

Part of the duet plugin — 25 skills, 6 commands, 1 agent 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/tslateman/duet/naming
Any agent
npx skills add tslateman/duet --skill naming
Clone the repo
git clone --depth 1 https://github.com/tslateman/duet

Made for: Claude Code, Codex.

Or install duet, the plugin that ships this one along with the rest of its 25 skills, 6 commands, 1 agent.

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 naming

README.md
[![agentmods](https://agentmods.dev/badge/skills/tslateman/duet/naming.svg)](https://agentmods.dev/skills/tslateman/duet/naming)
Your own site
<a href="https://agentmods.dev/skills/tslateman/duet/naming"><img src="https://agentmods.dev/badge/skills/tslateman/duet/naming.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,620 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 $0.00055 $0.01620
Opus 5 $0.00028 $0.00810
Sonnet 5 $0.00011 $0.00324
Haiku 4.5 $0.00006 $0.00162

Measured 3d ago against content hash bf4b229d0eb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

naming 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/naming/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Naming as Design

Overview

Naming difficulty is a design smell. When you struggle to name something, the abstraction is wrong. Use naming as a lens to surface confused boundaries, mixed responsibilities, and domain misunderstanding.

Benner's Four Principles

Every name balances four properties. When they conflict, make the tradeoff deliberate.

  1. Understandability, Describe the context it represents. A reader should know what it does without reading the implementation
  2. Conciseness, Use only the words necessary. Longer is not clearer if the extra words add no meaning
  3. Consistency, Same word means the same thing everywhere. Different things get different names
  4. Distinguishability, A name must be distinct from its neighbors. Similar names for different things cause bugs

See references/principles.md for detailed rules and naming smells.

Two Modes

Review Mode

Examine names in recently changed code:

  1. Read the changed code
  2. For each name, ask:
    • Does it pass all four principles?
    • Could a reader understand this without context?
    • Is the verb specific? ("process", "handle", "manage" almost never are)
    • Does it match the domain language?
  3. Surface violations with specific alternatives

Design Mode

When naming is hard, use the struggle as a diagnostic:

  1. What does this thing actually do? List its responsibilities
  2. If the list has more than one item, the naming problem is a design problem, split it
  3. Who calls it? What do they expect?
  4. If it disappeared, what would break? That's what it is
  5. What would the domain expert call it?

Naming Smells

Names that signal design confusion:

Smell Example What it reveals
Generic verb handleData, processRequest Unclear responsibility
Suffix -Manager, -Helper, -Utils UserManager, StringHelper God object or junk drawer
And/Or in name validateAndSave Two responsibilities
Type in name userList, nameString Redundant or wrong abstraction level
Negated boolean isNotReady, disableFeature Double negatives in conditions
Abbreviated beyond recognition usrSvcRsp Conciseness without understandability

Read the full file on GitHub · 166 lines

Files

What ships with it

1 file 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 · 166 lines · 55 tokens per session scan A bf4b229d0eb7

Subscribe to this mod's changes

naming is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 7d ago), licensed MIT. It adds 55 tokens to every session and 1,620 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.