Borrowing it
Nothing to install: this file belongs to openwong2kim/wmux. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/openwong2kim/wmux/main/.claude/skills/create-verification-skill/SKILL.mdgit clone --depth 1 https://github.com/openwong2kim/wmuxWrote 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/skills/openwong2kim/wmux/create-verification-skill)<a href="https://agentmods.dev/skills/openwong2kim/wmux/create-verification-skill"><img src="https://agentmods.dev/badge/skills/openwong2kim/wmux/create-verification-skill/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/skills/openwong2kim/wmux/create-verification-skill"><img src="https://agentmods.dev/badge/skills/openwong2kim/wmux/create-verification-skill.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 | $0.00097 | $0.01732 |
| Opus 5.5 | $0.00039 | $0.00693 |
| Sonnet 5.5 | $0.00019 | $0.00346 |
| Haiku 4.5 | $0.00010 | $0.00173 |
Grade A, and why
create-verification-skill scanned grade A with 1 finding 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 15d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Drive:** how can an agent interact with it programmatically? Existing harnesses first: Playwright/Cypress specs, expect scripts, PTY helpers, curl-able endpoints, a debug port, the repo's own dogfood scripts. Only th How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a verification skill
Every serious project needs a scripted way to drive the real app and prove behavior: launch it, exercise a feature the way a user would, and capture evidence. This skill generates that as a project-local Claude Code skill at .claude/skills/verify-<app>/, with its driver at scripts/control-<app>.mjs and its feature map at .claude/skills/verify-<app>/references/features/. You write the output for the next agent, not for a human: it will be read cold, mid-task, by an agent that has never seen the app.
In this repository the output already exists: .claude/skills/verify-wmux/ and scripts/control-wmux.mjs. Re-running this skill here means extending it (a new surface, a new launch mode), not starting over; for keeping it honest use /maintain-verification-skill.
1. Interview the repo, not the user
Answer these from the codebase and only ask the user what you cannot observe:
- Surface: what does a user actually touch? A web UI, a CLI/TUI, a desktop app, an API, a mobile app, a library? A repo can have several; pick the primary one and note the rest. (wmux: the Electron main window is primary; the
wmuxCLI, the MCP server and the phone web client are secondary.) - Run: how does the app start locally? Prefer the repo's own documented commands (package scripts, Makefile, README quickstart). Note ports, env vars, seed data, auth.
- Drive: how can an agent interact with it programmatically? Existing harnesses first: Playwright/Cypress specs, expect scripts, PTY helpers, curl-able endpoints, a debug port, the repo's own dogfood scripts. Only then pick a generic recipe: CDP for web and Electron, a tmux/PTY harness for CLI/TUI, plain HTTP for services.
- Observe: what evidence can be captured? ARIA snapshots, screenshots, terminal transcripts, response bodies, logs, exit codes, files and DB state.
- Isolate: can two instances run side by side (ports, data dirs, profiles, sockets)? If not, say so in the generated skill: refusing to double-drive a shared instance beats corrupting the user's session. Name the instance the driver must refuse to touch (for wmux: the owner's real instance, i.e. an empty
WMUX_DATA_SUFFIX, plus the shared-devand-portablesuffixes).
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.
- 15d ago First seen · 54 lines · 97 tokens per session scan A ef6dd03c7392
create-verification-skill is a skill published in the GitHub repository openwong2kim/wmux (437 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 1,732 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
Other skills, from other repositories
generate-e2e-tests
Walk a flow in the browser and write end-to-end tests (Playwright, Cypress, etc.) that reproduce it. Use when asked to create e2e coverage for a user flow.
smoke-test
Smoke-test a user flow end to end in a browser (login, checkout, signup, etc.) and verify the expected result. Use when asked to walk through a flow and confirm it still works.
qa-use
E2E testing and browser automation with qa-use CLI. Use when the user needs to run tests, verify features, automate browser interactions, or debug test failures.
alethia
Use Alethia, a patent-pending agent-native software runtime for executing and verifying application workflows, to interact with a real browser, run E2E checks, enforce safety policies, audit accessibility or security, and export signed evidence. Requires the @vitronai/alethia MCP server to be configured. Trigger…
playwright-tabbed-orchestration
Parent Agent uses playwright-tabbed to allocate browser tabs and partition tasks, then spawns child agents in parallel — each operating on its assigned tabid — for browser acceptance testing or automation, with a final aggregated summary. Suitable for multi-page validation, parallel module checks, and…
actionbook-web-test
Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…