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/doctorgit 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/doctor)<a href="https://agentmods.dev/commands/px0-ai/px0/doctor"><img src="https://agentmods.dev/badge/commands/px0-ai/px0/doctor.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 5.1 | $0.00000 | $0.00615 |
| Opus 5 | $0.00000 | $0.00308 |
| Sonnet 5 | $0.00000 | $0.00123 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
doctor 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 6d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
px0 doctor
Check that everything is wired up, and for anything that is not, print the exact
command that fixes it. A red line you cannot act on is the whole complaint
doctor exists to answer.
Implemented by px0/doctor.py.
px0 doctor [--quick] [--json]
Options
--quick
Skip the checks that need a live subprocess or a filesystem walk.
- Input: flag, no value. Default off.
- Use it in a hook or a prompt where the full pass would be too slow. This is the
mode
px0 updateruns to confirm an upgrade.
--json
Print the results as JSON, and nothing else.
- Input: flag, no value. Default off.
- Each check carries
ok,detail, and — when it failed —fix.
px0 doctor
px0 doctor --quick
px0 doctor --json | jq -r '.checks | to_entries[] | select(.value.ok == false) | .key'
The checks
| Check | What it confirms |
|---|---|
credentials |
.state/credentials.toml is mode 0600 — names the chmod and the path if not |
versions |
The version manifest opens and is consistent |
locks |
No stale process lock is left behind |
schema |
The store's schema version matches this binary's |
connections |
How many connector connections are configured |
workflows |
Every workflow file parses |
unreferenced_guidelines |
Guideline files no workflow inlines |
guideline_descriptions |
Guideline files with no description in their frontmatter, which a build cannot match a new workflow against |
update |
Whether a newer px0 is available |
daemon |
Whether the daemon is running |
harness |
The configured coding agent is on PATH and responds |
index |
qmd's version against the pinned one, and whether its local models have been consented to |
private_folder |
How much the private folder is holding back from retrieval |
private_folder is reported even when healthy, because the exclusion is
invisible in normal use: a brain pointed at a vault with its own work/ folder
can have all of it quietly missing from every search. See
px0 brain.
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.
- 6d ago First seen · 74 lines · 0 tokens per session scan A 8ae413028b59
doctor is a command published in the GitHub repository px0-ai/px0 (249 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 615 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
smoke-real-home
Run Alcove's read-mostly smoke against the current /.alcove home.
replay
Summarize one Agent Monitor session by id — header plus a concise transcript recap.
wiki-ingest
Ingest a source document into the LLM Wiki.
wiki-query
Query the LLM Wiki and synthesize an answer.
statusbar-doctor
Run cs doctor to diagnose why the status bar isn't showing what you expect.
release-note-csoar
Automates the creation of Cloud SOAR (Automation Service) release notes for platform updates, integration changes, and bug fixes.