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/milind-soni/axstream/axstream-teachgit 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-teach)<a href="https://agentmods.dev/commands/milind-soni/axstream/axstream-teach"><img src="https://agentmods.dev/badge/commands/milind-soni/axstream/axstream-teach.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 | $0.00018 | $0.00295 |
| Opus 5 | $0.00009 | $0.00148 |
| Sonnet 5 | $0.00004 | $0.00059 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
axstream-teach 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.
What it actually says
The user wants to teach axstream a repeatable macOS UI task: $ARGUMENTS
Follow the axstream skill's compile loop precisely:
- If the task description is empty, ask what task to teach.
- Check
axstream list --jsonfirst — if a macro for this task already exists, say so and stop (or offer to re-verify it). - Perform the task ONCE using the axstream MCP
acttool with a single assert-guarded batch (prefer key shortcuts over clicking chrome; never target text the batch itself types; end with an assert that only passes when the outcome is real). Usescreen_text/findto ground targets — not screenshots. - If the batch succeeded, save it with
write_macro: kebab-case name, a goodwhen_to_use, slots for the values that vary (with example values), and the terminal assert. - If a live re-run is side-effect-safe, run
verify_macroso it earns the verified stamp. If re-running would duplicate a side effect (sent message, created record), say why you're leaving it unverified. - Report: the macro name, its slots, verified state, and the one-liner to use it next time (
axstream replay <name> --slots ...).
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 · 15 lines · 18 tokens per session scan A ea01b73d53b6
axstream-teach is a command published in the GitHub repository milind-soni/axstream (20 stars, last pushed 27d ago), licensed MIT. It adds 18 tokens to every session and 295 once invoked, about $0.0001 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
显式启动一次隔离的 Windows Computer Use 任务.
planchette
Control a macOS window toward a goal — Claude picks the window and drives it.
screenshot
Take a screenshot of the current screen and describe what you see.
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.
screenshot
Screenshot a URL or document and read it visually.
barebrowse
Browser automation using the user's real browser with real cookies. Handles consent walls, login sessions, and bot detection automatically.