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/tanweai/pua/evidencegit 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/evidence)<a href="https://agentmods.dev/commands/tanweai/pua/evidence"><img src="https://agentmods.dev/badge/commands/tanweai/pua/evidence.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 | $0.00036 | $0.00201 |
| Opus 5 | $0.00018 | $0.00101 |
| Sonnet 5 | $0.00007 | $0.00040 |
| Haiku 4.5 | $0.00004 | $0.00020 |
Grade A, and why
evidence 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 4d 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.
- 4d ago First seen · 19 lines · 36 tokens per session scan A 2342f7d3b8aa
evidence is a command published in the GitHub repository tanweai/pua (19,579 stars, last pushed 5d ago), with no licence file. It adds 36 tokens to every session and 201 once invoked, about $0.0002 per session on Opus 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
run
Batch-execute every task in state/todo-ids.json (which only contains rows with Status == "To-Do" AND Exec == "Agent").
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.
init
Non-Claude harnesses only. Configure which models to use for task execution. Claude Code harnesses ignore this; they have built-in model selectors.
start
Move To-Do -> In Progress and emit the kickoff brief.
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.
log
Append a discussion entry to the task page.