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 skills/mtthsnc/tempest/qanpx skills add mtthsnc/tempest --skill qagit clone --depth 1 https://github.com/mtthsnc/tempestWhat 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 | $0.00094 | $0.01161 |
| Opus 5 | $0.00047 | $0.00580 |
| Sonnet 5 | $0.00019 | $0.00232 |
| Haiku 4.5 | $0.00009 | $0.00116 |
Grade A, and why
qa 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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qa — browser-driven UI acceptance via agent-browser
Overview
Prove the feature works the way a user would hit it — in a real browser. This skill drives
agent-browser to open pages, read the live accessibility tree, interact with real elements, and
assert observable state, then reports PASS/FAIL backed by a screenshot and a held assertion.
This is a STARTER skill — a generic spine. Rewrite the procedure, the flows you smoke-test, and the stop boundaries below to encode your own product's critical paths and acceptance bar.
This skill is harness-adaptive over the same agent-browser command vocabulary:
- On pi: prefer the native
agent_browsertool (from thepi-agent-browser-nativeextension). Input modes:args— raw CLI args, e.g.["open","<url>"],["snapshot","-i"],["click","@e2"],["screenshot","<path>"];job— astepsarray for multi-step smoke flows with actionsopen/click/fill/assertText/assertUrl/waitForDownload/screenshot; andqa— smoke/evidence mode that may reclassify diagnostics as failure. Use the companionagent_browser_web_searchto find URLs (don't drive Google's form — captcha risk). - On Claude Code (or any harness without that tool): drive the SAME
agent-browserCLI via the shell/Bash —agent-browser open <url>,agent-browser snapshot -i,agent-browser click @e1,agent-browser screenshot <path>, etc.
Prefer the native agent_browser tool if available; otherwise use the CLI via the shell. The
workflow is identical either way.
Setup: requires the agent-browser CLI on PATH (and on pi, the pi-agent-browser-native
extension). If it's missing, run the repo's scripts/doctor.sh or pi-agent-browser-doctor.
Procedure
1. Frame the acceptance
- Restate what "works" means as an observable outcome: a URL reached, text rendered, a download produced. If that's ambiguous, ask the user now.
- Pick the entry URL. If you only have a name, use
agent_browser_web_search(or a known direct URL) to find it — never drive a public search-engine form.
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.
- 2d ago First seen · 79 lines · 94 tokens per session scan A 2d9ae1b88e4c
qa is a skill published in the GitHub repository mtthsnc/tempest (2 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 1,161 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
test-browser
Run browser tests on pages affected by current PR or branch.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
browse
Fast headless browser for QA testing and site dogfooding. (gstack).
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
e2e-deployment-skill
Use this deployment skill to verify shared skills load during Playwright startup.
launch
Launch Code OSS (VS Code from sources) into an isolated throwaway profile with unique debug ports so you can drive it with @playwright/cli AND attach a Node debugger via dap-cli in the same session. Use when working on VS Code itself and you want to interact with the running workbench, automate chat or UI flows, test…