completion

A command that prints shell-completion scripts for px0, a command-line tool with many commands and arguments. It supports Bash, Zsh, and Fish.

In plain words
What is it for?
Generating completion setup for a shell and completing px0 groups, verbs, supported IDs, configuration keys, and recent run IDs.
Why use it?
It reduces the need to remember px0 command names, workflow IDs, configuration keys, and run IDs when typing commands.

Command

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/px0-ai/px0/completion
Clone the repo
git clone --depth 1 https://github.com/px0-ai/px0
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 446 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 $0.00000 $0.00446
Opus 5 $0.00000 $0.00223
Sonnet 5 $0.00000 $0.00089
Haiku 4.5 $0.00000 $0.00045

Measured 2d ago against content hash 12b55cc7ec9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

completion 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 2d 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.

docs/commands/completion.md · 68 lines

What it actually says

px0 completion

Print a shell completion script.

px0 has just over a hundred command nodes, and most arguments are ids you would otherwise have to remember: a workflow id, a guideline name, a config key, a run id. The scripts are generated from the argparse tree, so a new verb is completable the day it lands and a removed one stops being offered.

Implemented by px0/completion.py.

px0 completion {bash,zsh,fish}

shell (required)

Which shell to print a script for.

  • Input: bash, zsh, or fish.

bash

eval "$(px0 completion bash)"                                   # this session
px0 completion bash > /usr/local/etc/bash_completion.d/px0      # every session

zsh

eval "$(px0 completion zsh)"              # this session
px0 completion zsh > "${fpath[1]}/_px0"   # every session

fish

px0 completion fish > ~/.config/fish/completions/px0.fish

What gets completed

  • Every group and verb, from the parser itself. Flags hidden from --help stay hidden here too.
  • Workflow ids, for the commands that take one.
  • Config keys, for px0 config get|set|unset.
  • Run ids, for the commands that take one, newest 50.

Each script calls back into px0 --complete, which keeps the shell side small and lets the dynamic values come from the store.

px0 --complete (internal)

Hidden from --help, and not intended to be typed. Takes a partly typed command line and prints one candidate per line. It never prints an error: completion runs on every tab press, so a broken store must produce nothing rather than noise in the middle of your prompt.

Exit codes

Code When
0 Success
1 An unsupported shell was named
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. 2d ago First seen · 68 lines · 0 tokens per session scan A 12b55cc7ec9b

Subscribe to this mod's changes

completion is a command published in the GitHub repository px0-ai/px0 (241 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 446 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.