Borrowing it
Nothing to install: this file belongs to sabbour/agentweaver. 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/sabbour/agentweaver/dev/.github/skills/agentweaver-ui-harness/SKILL.mdgit clone --depth 1 https://github.com/sabbour/agentweaverWrote 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/sabbour/agentweaver/agentweaver-ui-harness)<a href="https://agentmods.dev/skills/sabbour/agentweaver/agentweaver-ui-harness"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/agentweaver-ui-harness/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/sabbour/agentweaver/agentweaver-ui-harness"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/agentweaver-ui-harness.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 | $0.00049 | $0.00505 |
| Opus 5 | $0.00024 | $0.00253 |
| Sonnet 5 | $0.00010 | $0.00101 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
agentweaver-ui-harness 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 8d 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
UI harness
Use this skill for a single UI-harness run: browser UI validation, persona browser-flow evidence capture, or investigation of a UI-reported issue. It is not the combined launcher; do not replace the API or MCP harnesses, or orchestrate a full cross-surface sweep here.
Read and follow the detailed CLI contract in scripts/ui-harness/SKILL.md. Invoke its
actual node scripts/ui-harness/agent-driver-ui/tools.mjs commands rather than
recreating browser steps with another Playwright interface.
Canvas interactions use the documented drag command with stable source/target test
IDs. It drives a genuine pointer down/move/up sequence and records failed attempts.
That contract now includes list-scenarios for the reviewed built-in UI catalog. Use
the separate harness-scenarios skill for cross-surface cataloging and persona
generation.
The auth pattern requires the managed Edge Default profile to satisfy Conditional Access (plain Chromium is blocked by Entra policy). Close all Edge windows first, then:
node scripts/ui-harness/login-edge-default.mjs --base-url <staging-url>
If Edge is already running with --remote-debugging-port=9222, append --cdp. The
script writes git-ignored state to scripts/ui-harness/.auth/ and a
session-token.txt for the API harness — never print or commit these.
Read scripts/ui-harness/SKILL.md Authentication section for full options (Option A /
Option B) and the legacy tool notes. Never automate the login flow or expose the
storage-state file.
Before running, check scripts/harness-shared/learnings.md (surface: ui or all)
for already-known bugs, environment facts, and scenario-design notes so they aren't
rediscovered from source each run.
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.
- 8d ago First seen · 46 lines · 49 tokens per session scan A 9f37d04e557e
agentweaver-ui-harness is a skill published in the GitHub repository sabbour/agentweaver (5 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 505 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 2026-08-31.
Other skills, from other repositories
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
playwright-visual-testing
Add, repair, or review Playwright visual regression tests for browser-facing .NET apps, including screenshot baselines, Pixelmatch thresholds, deterministic rendering, and GitHub Actions artifacts. USE FOR: toHaveScreenshot, page.screenshot visual checks, Pixelmatch/pngjs comparison scripts, visual baseline updates…
chrome-automation
A browser-automation toolkit for controlling Chrome to visit pages, interact with forms, collect data, run tests, and create screenshots or PDFs.
run-dashboard-e2e-local-changes
Run Playwright E2E (tests/e2e/) against the docker/ all-in-one harness so it reflects LOCAL code changes, not a stale cached image.
browser-check
Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.