inbox

inbox is a command for coding agents from px0-ai/px0. It costs 0 tokens per session (683 once invoked), scanned A, original, MIT.

A command-line inbox for results from scheduled or monitored workflows. It lets those runs leave readable entries instead of sending output only to a terminal or a file.

In plain words
What is it for?
Reviewing outputs from nightly jobs, watched runs, and other automated workflows. It can also report when a workflow writes its output to a file.
Why use it?
Scheduled jobs can finish when nobody is watching, so their results are easy to miss. This gives those results a place to review, read, archive, or clear.

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/inbox
Clone the repo
git clone --depth 1 https://github.com/px0-ai/px0

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 inbox

README.md
[![agentmods](https://agentmods.dev/badge/commands/px0-ai/px0/inbox.svg)](https://agentmods.dev/commands/px0-ai/px0/inbox)
Your own site
<a href="https://agentmods.dev/commands/px0-ai/px0/inbox"><img src="https://agentmods.dev/badge/commands/px0-ai/px0/inbox.svg" alt="Measured on agentmods" 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 683 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 $0.00683
Opus 5 $0.00000 $0.00342
Sonnet 5 $0.00000 $0.00137
Haiku 4.5 $0.00000 $0.00068

Measured 5d ago against content hash a4d744a58cbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

inbox 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 5d 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/inbox.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

px0 inbox

What your scheduled workflows produced, in a place you will actually look.

A workflow could route its output three ways, and on a schedule all three had the same problem. stdout goes to a terminal nobody is sitting at. file writes something you have to remember to open. A write tool posts somewhere else, which is fine when that somewhere is where you already look and useless when it is not. px0 did the work and then had nowhere to say so.

Implemented by px0/inbox.py.

px0 inbox [list] [--all] [--workflow ID] [--json]
px0 inbox read [entry-id] [--json]
px0 inbox archive <entry-id>
px0 inbox clear [--all]

What gets delivered

Scheduled and watched runs, by default. Manual ones do not: you were there for a manual run and have just read its output, where a nightly one produced something at 6am that nothing has told you about. A rehearsal never delivers — a dry run's output is a sample, not news.

A workflow can force either answer:

output:
  target: inbox          # the inbox is where this goes
output:
  target: file
  path: output/digest-{date}.md
  inbox: true            # write the file *and* say it arrived

inbox: false opts a scheduled workflow out. px0 config set inbox.auto false turns automatic delivery off everywhere.

An entry is small on purpose — what produced it, a preview, and where the whole thing is — because the inbox is a place to triage from, not a second copy of the output. Its title comes from the output's own first heading, since a workflow that already writes ## PRs you reviewed this week has said what the entry is better than any label px0 could synthesize.

px0 inbox / px0 inbox list

What is waiting, newest first.

--all

Include entries you have already read.

--workflow ID

Only entries from one workflow.

px0 inbox read

Reads one entry and marks it read. With no id, reads the oldest unread.

Where the entry announces a file, the file is read back from disk rather than from the copy taken at delivery — so you see what is there now, which is what matters when a later run has rewritten it.

Read the full file on GitHub · 95 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. 5d ago First seen · 95 lines · 0 tokens per session scan A a4d744a58cbb

Subscribe to this mod's changes

inbox is a command published in the GitHub repository px0-ai/px0 (241 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 683 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.