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.
npx agentmods add commands/px0-ai/px0/inboxgit clone --depth 1 https://github.com/px0-ai/px0Wrote 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/px0-ai/px0/inbox)<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>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 | $0.00000 | $0.00683 |
| Opus 5 | $0.00000 | $0.00342 |
| Sonnet 5 | $0.00000 | $0.00137 |
| Haiku 4.5 | $0.00000 | $0.00068 |
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.
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.
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.
- 5d ago First seen · 95 lines · 0 tokens per session scan A a4d744a58cbb
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.
Other commands, from other repositories
wiki-ingest
Ingest a source document into the LLM Wiki.
README
This folder gathers the project's 9 slash commands in a single place. Each command file specifies its traversal pattern (which Layer × Cycle cells it passes through, and in which cycle-stage flow) plus the Human Reviewer Gate. The nature of each role and the Layer × Cycle matrix have their SoT in…
wiki-discover
Discover unexpected connections in the LLM Wiki (Memex serendipity).
wiki-export
Export wiki to merged files for Claude.ai Project Knowledge.
wiki-news
Search for latest news related to the LLM Wiki's key topics.
wiki-query
Query the LLM Wiki and synthesize an answer.