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/approvalsgit 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/approvals)<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>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 | $0.00000 | $0.01625 |
| Opus 5 | $0.00000 | $0.00813 |
| Sonnet 5 | $0.00000 | $0.00325 |
| Haiku 4.5 | $0.00000 | $0.00162 |
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.
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
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.
- 5d ago First seen · 182 lines · 0 tokens per session scan A d96d09bc6e73
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.
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.