claude-docker: Command for Claude Code

.claude/commands/claude-vocab-section.md

claude-vocab-section is a command for Claude Code from VishalJ99/claude-docker. It costs 0 tokens per session (964 once invoked), scanned A, original, MIT.

A project vocabulary rule that makes the coding agent use definitions from a shared dictionary instead of guessing unfamiliar terms.

In plain words
What is it for?
Keeping a project dictionary in `docs/dictionary.md` and related term files, flagging unknown words, and creating entries with `/define-terms`.
Why use it?
It prevents misunderstandings when project-specific words are missing or resemble other terms. The agent must ask for clarification before continuing.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is VishalJ99/claude-docker's own configuration. It tells Claude Code how to work on claude-docker itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-docker configures →

Reuse

Borrowing it

Nothing to install: this file belongs to VishalJ99/claude-docker. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/VishalJ99/claude-docker/master/.claude/commands/claude-vocab-section.md
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 claude-vocab-section

README.md
[![agentmods](https://agentmods.dev/badge/commands/vishalj99/claude-docker/claude-vocab-section/github.svg)](https://agentmods.dev/commands/vishalj99/claude-docker/claude-vocab-section)
Your own site
<a href="https://agentmods.dev/commands/vishalj99/claude-docker/claude-vocab-section"><img src="https://agentmods.dev/badge/commands/vishalj99/claude-docker/claude-vocab-section/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-vocab-section

Your own site · 80×15
<a href="https://agentmods.dev/commands/vishalj99/claude-docker/claude-vocab-section"><img src="https://agentmods.dev/badge/commands/vishalj99/claude-docker/claude-vocab-section.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 964 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.00964
Opus 5 $0.00000 $0.00482
Sonnet 5 $0.00000 $0.00193
Haiku 4.5 $0.00000 $0.00096

Measured 11d ago against content hash 3143ac1c60e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

claude-vocab-section 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 11d 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/claude-vocab-section.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shared Vocabulary Protocol (add to CLAUDE.md)

Dictionary Location

  • Index: docs/dictionary.md — Load at session start
  • Full entries: docs/dictionary/[term].md — Read on-demand

How to Reference

  1. Load docs/dictionary.md (the index) at session start
  2. When you encounter a term from the index, read its full entry in docs/dictionary/
  3. Use the dictionary definition—NOT your general knowledge
  4. If a term is missing, follow the process below

When a Term is Missing

If a keyword in the user's query does not exist in the dictionary:

  1. Flag it: "⚠️ Term '[X]' not found in dictionary"
  2. Ask the user for a definition or description
  3. Run /define-terms "[X]" to create the entry using their input

Do NOT proceed with assumptions. The dictionary exists to prevent guesswork.

When a Potential Match Exists

If a keyword in the user's query is similar to (but not exactly) an existing term:

  1. Ask for confirmation: "Did you mean '[existing term]'?"
  2. If yes → use that term's definition
  3. If it's an alias → update the entry's Aliases field in docs/dictionary/[term].md to include the user's phrasing

Do NOT

  • ❌ Assume you know what a term means without checking
  • ❌ Skip the dictionary lookup because a term seems obvious
  • ❌ Proceed with ambiguous terms without asking

When Modifying Code

If your changes affect files listed in any dictionary term's "Code Locations":

  1. Re-read that term's full entry
  2. Verify your changes align with the defined behavior
  3. Update the dictionary entry if behavior has changed

Maintenance Responsibility

After ANY code change that:

  • Modifies a component/hook/store listed in a dictionary entry
  • Introduces a new domain concept
  • Changes the behavior of an existing concept

You MUST update docs/dictionary.md accordingly.

The Lookup Pattern

flowchart TD
    A[Receive User Instruction] --> B[Scan for Domain-Specific Terms]
    B --> C{Term in Dictionary?}
    C -->|Exact match| D[Read Full Entry]
    C -->|Partial match| E[Ask User: Did you mean X?]
    C -->|No match| F[Flag Missing Term]
    E -->|Yes| D
    E -->|No, it's an alias| G[Update Aliases in Entry]
    G --> D
    F --> H[Ask User for Definition]
    H --> I[Run /define-terms]
    I --> D
    D --> J[Proceed with Implementation]

Read the full file on GitHub · 112 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. 11d ago First seen · 112 lines · 0 tokens per session scan A 3143ac1c60e0

Subscribe to this mod's changes

claude-vocab-section is a command published in the GitHub repository VishalJ99/claude-docker (189 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 964 tokens. 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.