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/askgit clone --depth 1 https://github.com/px0-ai/px0What 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 | $0.01139 |
| Opus 5 | $0.00000 | $0.00570 |
| Sonnet 5 | $0.00000 | $0.00228 |
| Haiku 4.5 | $0.00000 | $0.00114 |
Grade A, and why
ask 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 3d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
px0 ask
One question, routed to whoever can answer it.
Everything px0 could do, it could only do if you already knew it was there.
px0 brain ask answers from material you have ingested and, by design, never
touches connectors or guidelines — so it can tell you what a post said about
caching and not what is on your calendar. Running a workflow meant knowing a
workflow existed and typing its id.
This is the front door. It decides who should answer, then answers.
Implemented by px0/route.py and px0/commands.py.
px0 ask ["<question>"] [--route ROUTE] [--explain] [--k N] [--yes] [--json]
px0 ask [--continue] [--no-remember]
Where a question can go
| Route | When |
|---|---|
memory |
px0 already knows, because you told it — see px0 memory |
brain |
The answer is in something you have read and kept |
workflow |
You have built something that does exactly this; run it |
tool |
One read-only call answers it, with every argument settled by the question |
answer |
None of the above — general knowledge, reasoning, or writing |
The route px0 chose is printed above the answer, so a question that went somewhere surprising says so rather than leaving you guessing.
px0 ask "what did that post say about backpressure?"
px0 ask "which pull requests did I review this week?"
px0 ask "when does my standup go out?"
Conversations
With no question and a terminal to type into, px0 ask opens a conversation
instead of answering once and forgetting:
px0 ask # ask, follow up, correct
px0 ask --continue # carry on the last one
Two things change once there is a thread. A follow-up is understood in terms of what came before, so "and last week?" — which names no subject and is unroutable alone — still lands. And a turn that reads as putting px0 right is marked as a correction.
Corrections are the reason this exists. What you say when an answer is wrong is the highest-signal thing you will say all day, and it used to be discarded the moment the command exited. At the end of a conversation px0 reads them for standing facts and offers to keep the ones worth keeping:
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.
- 3d ago First seen · 135 lines · 0 tokens per session scan A b9babf4f8b14
ask is a command published in the GitHub repository px0-ai/px0 (241 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,139 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-news
Search for latest news related to the LLM Wiki's key topics.
wiki-query
Query the LLM Wiki and synthesize an answer.
wiki-export
Export wiki to merged files for Claude.ai Project Knowledge.