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 skills add Threat-Vector-Security/guardian-agent --skill webapp-testinggit clone --depth 1 https://github.com/Threat-Vector-Security/guardian-agentWrote 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/threat-vector-security/guardian-agent/webapp-testing)<a href="https://agentmods.dev/skills/threat-vector-security/guardian-agent/webapp-testing"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/webapp-testing/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/threat-vector-security/guardian-agent/webapp-testing"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/webapp-testing.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 | $0.00055 | $0.00523 |
| Opus 5.5 | $0.00022 | $0.00209 |
| Sonnet 5.5 | $0.00011 | $0.00105 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
webapp-testing 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Webapp Testing
Use the MCP browser tools for browser work. Use Playwright for both read-only inspection and interaction. Prefer the Guardian wrapper tools when available.
Use browser-session-defense as the companion skill when the question is about browser security boundaries, risky browser actions, or the distinction between Guardian-managed browsing and the user's own browser activity.
Tool Selection
- Use Guardian wrapper tools first:
browser_navigate,browser_read,browser_links,browser_extract,browser_state,browser_act. - Use raw
mcp-playwright-*tools only when the wrapper surface cannot answer the question. - Do not use
mcp-playwright-browser_run_code; it is blocked by policy. - Avoid
evaluateunless the existing browser tools cannot answer the question and the action is worth approval.
Workflow
- Confirm how the app is started if it is not already running.
- Open the page with the lowest-power Guardian wrapper tool that can answer the question.
- Inspect before acting:
- page text or markdown
- semantic structure
- interactive elements
- screenshots or snapshots when visual state matters
- Identify selectors or target elements from observed state.
- Perform the minimum interaction needed to verify behavior.
- Capture evidence: screenshot, relevant console output, network details, or structured findings.
Read-Only Recon First
When the user asks "what is on this page?" or "why is this screen wrong?", prefer:
browser_readbrowser_linksbrowser_extractbrowser_statewhen interactive refs matter
Interactive Testing
For user journeys and bug reproduction:
- navigate first
- wait for the page to settle
- inspect the current state before clicking blindly
- use descriptive selectors or the browser snapshot output
- capture a screenshot before and after important interactions
Common Pitfalls
- Do not guess selectors before inspecting the current page state.
- Do not jump straight to raw MCP tools when the wrapper surface already covers the task.
- Do not stop at "it failed"; collect the screenshot, console messages, and any obvious network errors.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 58 lines · 55 tokens per session scan A bd32bd23213b
webapp-testing is a skill published in the GitHub repository Threat-Vector-Security/guardian-agent (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 523 once invoked, about $0.0002 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 skills, from other repositories
ux-acceptance-tester
Perform a goal-driven, black-box UX acceptance journey in a browser and report the path, friction, and observable outcome. Use only in an isolated tester context with a supplied start URL and brief.
ux-acceptance-coordinator
Coordinate black-box, agent-driven UX acceptance journeys against a disposable EmDash admin site. Use when preparing, dispatching, verifying, or reporting a manual browser journey performed by a separate tester agent. Do not use for deterministic Playwright tests or ordinary code review.
playwright-qa
Automated visual QA testing using Playwright — navigate web apps like a real user, capture screenshots, find bugs, and fix them.
playwright-page-objects
Use when creating page objects or refactoring Playwright E2E tests for better maintainability with Page Object Model patterns.
test-browser
Run browser tests on pages affected by current PR or branch.
playwright-praman-sap-testing
Package: playwright-praman Import: import { test, expect } from 'playwright-praman' Purpose: Primary instruction set for Praman AI agents (planner, generator, healer).