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.
git clone --depth 1 https://github.com/tanweai/puaWrote 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/tanweai/pua/p9)<a href="https://agentmods.dev/commands/tanweai/pua/p9"><img src="https://agentmods.dev/badge/commands/tanweai/pua/p9/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/tanweai/pua/p9"><img src="https://agentmods.dev/badge/commands/tanweai/pua/p9.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.00083 |
| Opus 5.5 | $0.00024 | $0.00033 |
| Sonnet 5.5 | $0.00012 | $0.00017 |
| Haiku 4.5 | $0.00006 | $0.00008 |
Grade A, and why
p9 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 1mo 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 1mo ago First seen · 6 lines · 61 tokens per session scan A b9e3e9d470f9
p9 is a command published in the GitHub repository tanweai/pua (19,715 stars, last pushed 1mo ago), with no licence file. It adds 61 tokens to every session and 83 once invoked, about $0.0002 per session on Opus 5.5. 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
refresh
Auto-enumerate the agent-runnable To-Do set and write it to state/todo-ids.json. No arguments. The operator's only job upstream is to mark rows in Notion with Exec=Agent; refresh then fetches them via the Notion REST API and the sidecar is the enumeration substrate for run.
tree
Emit a compact indented view of the active task hierarchy and refresh state/task-tree.json. This is the primary tool for understanding the board's shape before adding new work.
start
Move To-Do -> In Progress and emit the kickoff brief.
scaffold
The single-shot setup command. Builds the entire Notion workspace from scratch — Hub page, Tasks database with the full schema below, General Guidance page, Resources page, default corpus pages (General, Recurring), and every linked DB view. There is no public Notion template to duplicate; this command IS the setup.…
suggest
Add a row in Suggestion status. Structure check runs inside suggest — the subagent enforces it, not just the orchestrator. The orchestrator decides the shape (which parent, whether a container is needed); suggest verifies that decision was made rather than silently creating a root-level row.
discuss
Begin clarification on a Suggestion. Flips status to Discussion and prepares the agent to ask clarifying questions.