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/updategit 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 | $0.00820 |
| Opus 5 | $0.00000 | $0.00410 |
| Sonnet 5 | $0.00000 | $0.00164 |
| Haiku 4.5 | $0.00000 | $0.00082 |
Grade A, and why
update 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
px0 update and px0 version
Upgrade px0 in place, apply any pending store-schema migrations, and roll back if an upgrade goes wrong.
Implemented by px0/update.py.
px0 update [--check] [--channel CHANNEL]
px0 update rollback
px0 version
px0 update
Check PyPI for a newer release and install it through whichever mechanism installed px0 — pipx or pip, detected automatically.
A successful update then, in order: applies pending schema migrations, appends
the result to .state/update-history.json, restarts a running daemon, and
finishes with a quick doctor pass.
--check
Report whether an update is available and stop. Installs nothing.
- Input: flag, no value. Default off.
px0 update --check
--channel CHANNEL
Which release channel to consult.
- Input:
stableorbeta. - Default:
update.channel, which ships asstable. - Not functionally enforced in this build;
px0 updatereports when no release manifest is configured.
px0 update
px0 update --channel beta
Schema migrations
The store has an on-disk schema version, recorded in .state/schema. When a px0
release changes the layout in a way an older store cannot read, it ships a
migration, and px0 update applies every one newer than the store's version, in
order.
Migrations are forward-only. They are recorded in the update history, and
each is committed to the store's own version history so px0 changes shows it.
If the schema marker cannot be read, the update refuses rather than assuming version 1 — assuming would re-run every migration against a store that may already be migrated.
The current schema is 2. Version 2 renamed knowledge/ to brain/ and
knowledge.path to brain.path. Its migration moves the folder, rewrites the
config key, completes the folder layout, and drops the stale qmd collection the
rename would otherwise orphan. A brain kept outside the store — a notes vault —
is left exactly where it is.
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.
- 2d ago First seen · 122 lines · 0 tokens per session scan A 4ae58c63708d
update 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 820 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.