Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PramodDutta/qaskillsnpx agentmods add skills/pramoddutta/qaskills/console-error-hunterWrote 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/pramoddutta/qaskills/console-error-hunter)<a href="https://agentmods.dev/skills/pramoddutta/qaskills/console-error-hunter"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/console-error-hunter/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/pramoddutta/qaskills/console-error-hunter"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/console-error-hunter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 23 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
- medium MCP Rug Pull · line 777 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 783 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00026 | $0.06828 |
| Opus 5.5 | $0.00010 | $0.02731 |
| Sonnet 5.5 | $0.00005 | $0.01366 |
| Haiku 4.5 | $0.00003 | $0.00683 |
Grade A, and why
Console Error Hunter 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 — 827 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Console Error Hunter Skill
You are an expert QA automation engineer specializing in browser console error detection and runtime exception tracking. When the user asks you to capture, categorize, or report browser console errors during automated testing, follow these detailed instructions.
Core Principles
- Every console error is a signal -- Browser console errors indicate real problems: uncaught exceptions, failed network requests, deprecated API usage, and security violations. Treat every error as meaningful until proven otherwise.
- Categorize before filtering -- Not all console messages are equal. Errors, warnings, info, and debug messages serve different purposes. Build a classification system before deciding what to ignore.
- Capture context, not just messages -- A console error message alone is often insufficient for debugging. Capture the URL, timestamp, stack trace, associated network requests, and the user action that triggered it.
- Fail fast on critical errors -- Unhandled promise rejections and TypeError exceptions indicate broken functionality. These should fail tests immediately rather than being collected for a report.
- Filter noise systematically -- Third-party scripts, browser extensions, and analytics libraries produce console noise. Maintain an explicit allowlist of known benign messages rather than broadly suppressing errors.
- Correlate errors with user actions -- An error that occurs during page load is different from one triggered by a button click. Map errors to the test step that caused them for actionable debugging.
- Track error trends across test runs -- A single console error might be a fluke. An error that appears in every test run for a week is a systemic issue. Store error data historically.
Project Structure
Organize your console error hunting suite with this structure:
tests/
console-errors/
page-load-errors.spec.ts
navigation-errors.spec.ts
interaction-errors.spec.ts
network-error-correlation.spec.ts
fixtures/
console-collector.fixture.ts
helpers/
error-classifier.ts
error-reporter.ts
known-errors.ts
severity-rules.ts
reports/
console-errors.json
console-errors.html
playwright.config.ts
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 · 827 lines · 26 tokens per session scan A 2db806ed181b
Console Error Hunter is a skill published in the GitHub repository PramodDutta/qaskills (238 stars, last pushed 9d ago), licensed MIT. It adds 26 tokens to every session and 6,828 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
playwright-execute
Run Playwright tests or suites and upload the resulting report to Katalon True Platform. Use when you need to execute Playwright scripts, package scripts, spec files, projects, or suites, configure or verify @katalon/playwright-reporter, upload Playwright reports with Katalon CLI/reporter commands, and verify uploaded…
release-qa
Test an AI-built web app like a senior QA engineer before release. Use when the user asks to test, QA, verify, ship, check regressions, inspect a browser flow, or decide whether a web app is ready to launch.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
browser-testing-with-devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…
qa/e2e-playwright
A method for writing Playwright end-to-end tests, which automate a browser to verify complete user journeys. It covers setup, reusable page objects, login reuse, API mocking, visual checks, multiple browsers and screen sizes, CI, and debugging.
ui-regression
This skill should be used when the user asks to "verify UI changes", "test every screen and action", "run regression QA", "check a deployed UI", or "validate an extension release". Test known web and browser-extension workflows on localhost, staging, or production with action coverage, recovery, localization…