workflows

A command-line system for creating and running automated jobs described in Markdown files with YAML settings. Each workflow records its trigger, permitted tools, instructions, and output destination.

In plain words
What is it for?
Automating recurring tasks, running them with inputs and time limits, testing them with dry runs or fixtures, checking their health, and choosing whether results go to the terminal or a file.
Why use it?
Repeatable jobs are difficult to define and maintain when their steps and settings are scattered. This provides commands to create, run, inspect, validate, edit, replay, improve, copy, rename, or remove workflows.

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/workflows
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 9,776 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 $0.09776
Opus 5 $0.00000 $0.04888
Sonnet 5 $0.00000 $0.01955
Haiku 4.5 $0.00000 $0.00978

Measured 2d ago against content hash 39ed3c19a6a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflows 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/workflows.md · 1,112 lines

How it starts

The opening of the file, as written. The whole thing — 1,112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

px0 workflows

A workflow is a Markdown file with YAML frontmatter describing a job px0 can run: its trigger, the tools it may call, the guidelines it inlines, and where its output goes. px0 interviews you for one and builds it.

Implemented by px0/workflow.py (the file format), px0/builder.py (building from a description), and px0/runner.py (execution).

px0 workflows new
px0 workflows run [workflow] [--input K=V] [--output {stdout,file}] [--timeout DURATION] [--no-retry] [--dry-run] [--stdin] [--quiet] [--json]
px0 workflows edit [workflow] [--yes] [--no-clarify] [--no-discover]
px0 workflows health [workflow] [--since AGE] [--fix] [--yes] [--json]
px0 workflows improve [workflow] [--since AGE] [--dry-run] [--show-evidence] [--yes] [--no-clarify] [--no-discover] [--json]
px0 workflows recipes [--json]
px0 workflows replay <workflow> [--run ID] [--against FILE] [--fixtures] [--forget] [--json]
px0 workflows list
px0 workflows show <workflow> [--json]
px0 workflows validate [workflow] [--json]
px0 workflows delete [workflow] [--yes]
px0 workflows rename <workflow> <new-id>
px0 workflows copy <workflow> <new-id>
px0 workflows templatize [workflow] [--to NEW-ID] [--candidates] [--dry-run] [--yes] [--json]
px0 workflows disable <workflow>
px0 workflows enable <workflow>

px0 workflows new

Turn a description into a workflow file. px0 interviews you for it, asks what is ambiguous, finds the tools the job needs, authorizes them, writes the workflow, and saves it under workflows/.

  • Arguments: none — px0 workflows new always opens the interview below.
px0 workflows new

The interview

px0 asks for one thing at a time until it has what a workflow file must pin down:

The job what should happen
The sources what it reads: which service, account, repository, channel, folder, or your own notes
The delivery what it produces and where that goes
The cadence on demand, on a schedule, or when something happens
Done looks like what makes the output right rather than merely produced

Read the full file on GitHub · 1,112 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. 2d ago First seen · 1,112 lines · 0 tokens per session scan A 39ed3c19a6a4

Subscribe to this mod's changes

workflows 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 9,776 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.