approvals

approvals is a command for coding agents from px0-ai/px0. It costs 0 tokens per session (1,625 once invoked), scanned A, original, MIT.

A review queue for tool calls that would change something, allowing a person to inspect and approve them before they run.

In plain words
What is it for?
Use it to list, inspect, edit, approve, reject, or remove pending tool calls.
Why use it?
It lets an agent prepare an action without carrying it out in your name until someone confirms it.

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/approvals
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 approvals

README.md
[![agentmods](https://agentmods.dev/badge/commands/px0-ai/px0/approvals.svg)](https://agentmods.dev/commands/px0-ai/px0/approvals)
Your own site
<a href="https://agentmods.dev/commands/px0-ai/px0/approvals"><img src="https://agentmods.dev/badge/commands/px0-ai/px0/approvals.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 1,625 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 $0.01625
Opus 5 $0.00000 $0.00813
Sonnet 5 $0.00000 $0.00325
Haiku 4.5 $0.00000 $0.00162

Measured 5d ago against content hash d96d09bc6e73, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

approvals 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/approvals.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

px0 approvals

Write tool calls that wait for a person.

px0's trust model was binary: a tool either mutates something or it does not, and a workflow either may call it or may not. --dry-run stubs every write, which rehearses a workflow but never does the work. There was no middle — no way to say draft it and ask me — so anything that speaks in your name had to be handed the real capability up front, on the strength of a plan you read once.

This is that middle. A held-back call is not executed: it is written down in full — tool, arguments, the run that drafted it, and what that run produced — and the model is told it has been queued, so the run still finishes and still produces its output. You see exactly what would be sent, and approving it makes the call for real.

Implemented by px0/approvals.py.

px0 approvals [list] [--all] [--workflow ID] [--json]
px0 approvals show <approval-id> [--json]
px0 approvals edit <approval-id> [--set KEY=VALUE] [--note WHY]
px0 approvals approve <approval-id> [--yes]
px0 approvals reject <approval-id> [--reason WHY]
px0 approvals purge [--days N]

Turning it on

Per workflow, in its frontmatter — this wins over the store-wide default in both directions:

confirm: true                  # every write this workflow makes
confirm:                       # or only these
  - slack.post_message

Store-wide, for everything that does not say otherwise:

px0 config set tools.confirm_writes true

Read tools never wait. A queue that fills up with searches is one nobody reads, and the point of the gate is the calls that leave a mark.

px0 approvals / px0 approvals list

What is waiting, oldest first — unlike every run listing in px0, because this is a queue rather than a history and the thing most likely to have gone stale is the thing you most need to see.

--all

Include ones already sent, rejected, or expired.

--workflow ID

Only drafts from one workflow.

px0 approvals show

Read the full file on GitHub · 182 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 · 182 lines · 0 tokens per session scan A d96d09bc6e73

Subscribe to this mod's changes

approvals is a command published in the GitHub repository px0-ai/px0 (241 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,625 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.