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/milind-soni/axstreamWrote 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/milind-soni/axstream/axstream-stats)<a href="https://agentmods.dev/commands/milind-soni/axstream/axstream-stats"><img src="https://agentmods.dev/badge/commands/milind-soni/axstream/axstream-stats/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/milind-soni/axstream/axstream-stats"><img src="https://agentmods.dev/badge/commands/milind-soni/axstream/axstream-stats.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 | $0.00016 | $0.00151 |
| Opus 5.5 | $0.00006 | $0.00060 |
| Sonnet 5.5 | $0.00003 | $0.00030 |
| Haiku 4.5 | $0.00002 | $0.00015 |
Grade A, and why
axstream-stats 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.
What it actually says
Benchmark an axstream macro: $ARGUMENTS
- If no macro name given, run
axstream list --jsonand pick the most-used-looking verified macro (or ask). - Run
axstream bench <name> --warmup 1 --runs 3(only if the macro is side-effect-safe — refuse to bench anything that sends/pays/deletes, and say why). - Present a compact table: per-op p50/p95 and the total, then one comparison line: what this task would roughly cost via screenshot-driven computer use (~5-15s per step) vs the measured replay total.
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 · 10 lines · 16 tokens per session scan A 5781cfda7ccc
axstream-stats is a command published in the GitHub repository milind-soni/axstream (20 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 151 once invoked, about $0.0001 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
CHANGELOG
Command "CHANGELOG" from bytedance/UI-TARS-desktop, covering 0.4.0 2024-12-10 - add logging, 1.2.29, 1.2.28, 1.2.26 and 1.2.25.
TODO
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra.
run
A command that starts a planned, isolated Windows computer-use task. It follows prepared steps, checks the computer setup, uses screenshots when needed, and reports what was actually verified.
doctor
A command that diagnoses the Computer Use plugin, its environment, and its mapped capabilities. Computer Use lets an agent interact with a computer through supported actions.
trace
A command for viewing or exporting privacy-filtered Computer Use activity traces. A trace is a record of actions taken during a computer-use session, and the command supports status, listing recent traces, and confirmed export.
benchmark
A command that produces a report measuring Computer Use capabilities, such as task completion and tool activity. Computer Use means controlling applications through an interactive computer interface.