runs

runs is a command for coding agents from px0-ai/px0. It costs 0 tokens per session (2,472 once invoked), scanned A, original, MIT.

Commands and an interactive browser for records of every px0 execution, including workflow runs and requests to its stored knowledge.

In plain words
What is it for?
Use them to browse or filter runs, inspect a specific execution, investigate failures, and review triggers, tool calls, results, and outcomes.
Why use it?
They preserve summaries and machine-readable events after full logs expire, so you can inspect what happened and whether it succeeded.

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/runs
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 runs

README.md
[![agentmods](https://agentmods.dev/badge/commands/px0-ai/px0/runs.svg)](https://agentmods.dev/commands/px0-ai/px0/runs)
Your own site
<a href="https://agentmods.dev/commands/px0-ai/px0/runs"><img src="https://agentmods.dev/badge/commands/px0-ai/px0/runs.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 2,472 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 $0.02472
Opus 5 $0.00000 $0.01236
Sonnet 5 $0.00000 $0.00494
Haiku 4.5 $0.00000 $0.00247

Measured 5d ago against content hash db9969a329ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runs 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/runs.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

px0 runs

Every execution — a workflow run, or a brain ask — is recorded: what triggered it, which tools it called, what it produced, and whether it succeeded. Records outlive their logs, so history stays inspectable after the logs age out.

A run leaves three artifacts behind, all under logs.path:

Artifact Kept for What it is for
The record (records/) logs.record_retention_days, a year by default The run's summary. What every listing and px0 workflows health reads
The raw log (runs/) logs.retention_days, a fortnight The full prompts and replies, for a person reading one run
The event stream (events/) with the raw log One JSON object per turn, tool call, and outcome — the machine-readable account

Nothing derives a verdict from the raw log, because the raw log is usually gone.

Implemented by px0/runs.py (records, events, and retention) and px0/runs_tui.py (the interactive browser).

px0 runs                                 # interactive browser
px0 runs list [--workflow ID] [--failed] [--since WHEN] [--running] [--json] [--workflow ID] [--failed] [--since WHEN] [--json]
px0 runs show <run_id>
px0 runs output <run_id>
px0 runs logs <run_id> [--follow|-f]
px0 runs rerun <run_id>
px0 runs why <run_id>
px0 runs cancel <run-id> [--force]
px0 runs prune [--dry-run]
px0 runs open <run-id>
px0 runs mark <run-id> [--good [NOTE] | --bad [NOTE] | --clear] [--note NOTE]
px0 runs events <run-id> [--json]
px0 runs stats [--since WHEN] [--json]

px0 runs with no verb

Opens an interactive run browser. This is the one group where omitting the verb is not an error.

Piped or redirected it prints the listing instead, so px0 runs | head behaves like px0 runs list rather than failing for want of a terminal.


px0 runs list

Past runs, newest first.

--workflow ID

Only runs of one workflow.

  • Input: a workflow id.

--failed

Only runs that did not succeed.

Read the full file on GitHub · 347 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 · 347 lines · 0 tokens per session scan A db9969a329ae

Subscribe to this mod's changes

runs is a command published in the GitHub repository px0-ai/px0 (246 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,472 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.