define-terms

define-terms is a command for Claude Code from VishalJ99/claude-docker. It costs 10 tokens per session (1,335 once invoked), scanned A, original, MIT.

A command for creating and updating a project dictionary of domain-specific terms, with links back to relevant code.

In plain words
What is it for?
Adding entries under `docs/dictionary.md` and `docs/dictionary/`, checking terminology, and enabling agents to trace definitions to code.
Why use it?
It gives the project one agreed source of meaning and exposes duplicate, vague, overlapping, or contradictory definitions.

Command 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 commands/vishalj99/claude-docker/define-terms
Clone the repo
git clone --depth 1 https://github.com/VishalJ99/claude-docker

Made for: Claude Code.

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 define-terms

README.md
[![agentmods](https://agentmods.dev/badge/commands/vishalj99/claude-docker/define-terms.svg)](https://agentmods.dev/commands/vishalj99/claude-docker/define-terms)
Your own site
<a href="https://agentmods.dev/commands/vishalj99/claude-docker/define-terms"><img src="https://agentmods.dev/badge/commands/vishalj99/claude-docker/define-terms.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,335 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 $0.00010 $0.01335
Opus 5 $0.00005 $0.00668
Sonnet 5 $0.00002 $0.00267
Haiku 4.5 $0.00001 $0.00134

Measured 4d ago against content hash ba7d6ab9cd46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

define-terms 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 4d 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/commands/define-terms.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Define Terms

Terms to Define

$ARGUMENTS

Before Starting

  1. Check for inconsistencies in the provided terms — flag duplicates, overlapping concepts, or contradictory definitions
  2. Ask for clarification if any term is vague, ambiguous, or could have multiple interpretations
  3. Do not proceed until inconsistencies are resolved

Mode

If docs/dictionary.md and docs/dictionary/ already exist, update them by adding new entries. Do not recreate or overwrite existing entries unless explicitly asked.

Initialisation: Ensure project CLAUDE.md Has Vocabulary Protocol

Check if .claude/CLAUDE.md contains a "Shared Vocabulary Protocol" section.

If not present:

  1. Read `~/.claude/commands/claude-vocab-section.md
  2. Append its contents to the project-level CLAUDE.md

This ensures agents know how to use the dictionary at runtime.

Objective

Generate entries in docs/dictionary.md index file that serves as the canonical source of truth for domain-specific terminology in this project. The index is loaded at session start; full entries are read on-demand.

The Problem This Solves

Terms like "committed state" or "editor" have project-specific meanings that differ from their general usage. Without explicit definitions, agents must guess—leading to misaligned implementations.


Step 1: Audit & Discovery

Before writing definitions, conduct a full audit:

  1. Review the provided terms (listed above in $ARGUMENTS)
  2. Scan the codebase for:
    • Component names that imply domain concepts (e.g., CommitWeekModal, BundleEditor)
    • State variables with domain meaning (e.g., isCommitted, editorMode)
    • Comments or docs referencing undefined jargon
  3. Identify gaps - Ask me clarifying questions for any term that is:
    • Ambiguous
    • Has multiple possible interpretations
    • References UI/UX states not fully described

Output a list of all discovered terms before proceeding. Wait for my confirmation before writing the dictionary.

Read the full file on GitHub · 181 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. 4d ago First seen · 181 lines · 10 tokens per session scan A ba7d6ab9cd46

Subscribe to this mod's changes

define-terms is a command published in the GitHub repository VishalJ99/claude-docker (188 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 1,335 once invoked, about $0.0001 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.