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.
git clone --depth 1 https://github.com/wbingli/zsh-claudecode-completionWrote 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.
[](https://agentmods.dev/commands/wbingli/zsh-claudecode-completion/update-completions)<a href="https://agentmods.dev/commands/wbingli/zsh-claudecode-completion/update-completions"><img src="https://agentmods.dev/badge/commands/wbingli/zsh-claudecode-completion/update-completions/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.
<a href="https://agentmods.dev/commands/wbingli/zsh-claudecode-completion/update-completions"><img src="https://agentmods.dev/badge/commands/wbingli/zsh-claudecode-completion/update-completions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00011 | $0.03730 |
| Opus 5 | $0.00005 | $0.01865 |
| Sonnet 5 | $0.00002 | $0.00746 |
| Haiku 4.5 | $0.00001 | $0.00373 |
Grade A, and why
update-completions 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.
How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are updating the zsh completion script for Claude Code CLI. Follow these steps:
Step 1: Check for Force Flag and Compare Versions
-
Check if
--forcewas passed as an argument to this command (check $ARGUMENTS). -
If
--forceis NOT present:- Get the installed Claude version:
claude --version - Read the tracked version from the
claude-versionfile in this repository - Compare the versions. If they match or the installed Claude version is lower than the tracked version, report "Completions are up to date" and stop.
- Get the installed Claude version:
-
If
--forceIS present:- Skip version comparison
- Report "Force flag detected, regenerating completions regardless of version"
- Continue to Step 2
Step 2: Gather Help Output (if versions differ)
Run these commands to get the current CLI structure:
claude --helpclaude mcp --helpclaude plugin --helpclaude install --help
Important: How to gather a comphrehensive help output
Above are just examples, but you should gather help output for all top-level commands and subcommands as needed to fully capture the CLI structure for completions. Store this output for use in the next step.
It may have multiple sub commands. For example, claude plugin will have its own set of subcommands. In the meanwhile, claude plugin marketplace may also have its own set of subcommands. Make sure to capture all levels of subcommands as needed.
You need to iterate through every subcommand to get their help output as well. For example, start with claude --help. You will have all the top level commands and options. For each top level command, you will need to run claude <top-level-command> --help to get its subcommands and options. If any of those subcommands have their own subcommands, you will need to run claude <top-level-command> <subcommand> --help as well, and so on, until you have captured the full hierarchy of commands and options.
Hidden Commands
Some Claude CLI commands are hidden — they work but are not listed in claude --help. These must be included in completions even though they won't appear in the help output. Always gather their help output separately:
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.
- 11d ago First seen · 280 lines · 11 tokens per session scan A c4dfd710a939
update-completions is a command published in the GitHub repository wbingli/zsh-claudecode-completion (56 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 3,730 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.