What is zsh-claudecode-completion CLAUDE.md?

Project instructions for maintaining zsh tab completion for the Claude Code command-line tool. Tab completion suggests commands, options, and file paths as someone types in a terminal.

Use it when updating Claude Code command or option completion, changing the Oh My Zsh plugin entry point, or documenting the plugin’s architecture.

It explains where the completion logic lives and keeps changes consistent with the plugin’s limited purpose. It also records which Claude Code version the suggestions support.

How wbingli/zsh-claudecode-completion configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to wbingli/zsh-claudecode-completion. 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/wbingli/zsh-claudecode-completion/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/wbingli/zsh-claudecode-completion

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/wbingli/zsh-claudecode-completion/claude-md/github.svg)](https://agentmods.dev/instructions/wbingli/zsh-claudecode-completion/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/wbingli/zsh-claudecode-completion/claude-md"><img src="https://agentmods.dev/badge/instructions/wbingli/zsh-claudecode-completion/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/wbingli/zsh-claudecode-completion/claude-md"><img src="https://agentmods.dev/badge/instructions/wbingli/zsh-claudecode-completion/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 807 This file is loaded in full into every session.

When invoked 807 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00807	$0.00807
Opus 5.5	$0.00323	$0.00323
Sonnet 5.5	$0.00161	$0.00161
Haiku 4.5	$0.00081	$0.00081

Measured 25d ago against content hash 8b97a0a0f14b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zsh-claudecode-completion CLAUDE.md 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 25d 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.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

A minimal zsh completion plugin for the Claude Code CLI. Provides tab completion only—no aliases, wrapper functions, or opinionated workflows.

Key Files

_claude - Main completion script using zsh's #compdef system. Contains all completion logic for commands, subcommands, and flags.
zsh-claudecode-completion.plugin.zsh - Oh My Zsh plugin entry point. Copies _claude to $ZSH_CACHE_DIR/completions/ to avoid fpath duplication issues.
claude-version - Tracks which Claude CLI version the completions are based on.
.claude/commands/ - Slash commands for Claude Code (e.g., /update-completions).

Architecture

The completion system uses standard zsh completion functions:

_arguments for flag/option handling
_describe for listing commands with descriptions
_files for path completion
Context variables: $words (command line words), CURRENT (cursor position)

The _claude script uses a case statement with early returns to route between subcommands (mcp, plugin, install, etc.).

Development Notes

No build system or linting—pure zsh scripts only.

To test changes manually:

Source the plugin: source zsh-claudecode-completion.plugin.zsh
Reload completions: autoload -Uz compinit && compinit
Test with: claude <TAB>

Automated tests live under scripts/tests/ and are driven by scripts/verify-completions.sh. Each test-*.sh covers one feature (syntax, global flags, mcp subcommand, nested positionals, _claude_session_ids). The runner also accepts a single test name: ./scripts/verify-completions.sh test-session-ids. Requires zsh, expect, and jq.

Known Patterns

Avoid nested helper functions in _claude—they caused duplicate completions (see commit ff451fe). The exception is leaf value completers (_claude_session_ids, _claude_models, _claude_agents, _claude_mcp_servers, _claude_installed_plugins, ...): they only add matches, are used as _arguments actions, and must pass "$@" on to _describe/compadd
Use flat structure with explicit return statements after each case block
$words is trimmed to start at the subcommand, and again at each nested level, so positional specs count from the first real argument. Don't use ':cmd:' placeholders
Value completers read Claude's own files (~/.claude.json, .mcp.json, ~/.claude/plugins/*.json), honor CLAUDE_CONFIG_DIR, and never call the claude binary or the network
Plugin copies _claude to cache directory instead of adding to fpath—prevents duplicates when plugin dir is symlinked

Read the full file on GitHub · 64 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.

25d ago Changed · +1 lines · +122 tokens per session 8b97a0a0f14b
26d ago Changed · +1 lines · +43 tokens per session ebef98a41b94
2mo ago First seen · 62 lines · 642 tokens per session scan A 17a2c8204702

Subscribe to this mod's changes

zsh-claudecode-completion CLAUDE.md is an instructions file published in the GitHub repository wbingli/zsh-claudecode-completion (61 stars, last pushed yesterday), licensed MIT. It adds 807 tokens to every session, about $0.0032 per session on Opus 5.5. 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.

zsh-claudecode-completion CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
zsh-claudecode-completion CLAUDE.mdwbingli/zsh-claudecode-completion	Instructions file	61	yesterday	MIT	A	807	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

zsh-claudecode-completion: Instructions file for Claude Code