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 jrpool/kilotest --skill kilotest-overviewgit clone --depth 1 https://github.com/jrpool/kilotestWrote 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/jrpool/kilotest/kilotest-overview)<a href="https://agentmods.dev/skills/jrpool/kilotest/kilotest-overview"><img src="https://agentmods.dev/badge/skills/jrpool/kilotest/kilotest-overview/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/jrpool/kilotest/kilotest-overview"><img src="https://agentmods.dev/badge/skills/jrpool/kilotest/kilotest-overview.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 | $0.00085 | $0.00623 |
| Opus 5.5 | $0.00034 | $0.00249 |
| Sonnet 5.5 | $0.00017 | $0.00125 |
| Haiku 4.5 | $0.00009 | $0.00062 |
Grade A, and why
kilotest-overview 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 yesterday.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kilotest overview and workflow
Kilotest tests web pages for front-end quality: accessibility, usability, and web standards, including HTML, CSS, ARIA, and WCAG.
Kilotest integrates an ensemble of 12 independent rule engines to test a web page and stores the results as a structured report, from which it exposes results at selectable granularities.
Report hierarchy
Results are organized as a hierarchy:
- Tested pages.
- For each tested page, reports from the tests of the page.
- For each report, issues reported.
- For each issue, violators of rules belonging to the issue (a violator is an element or the whole page).
- For each violator, diagnoses by rule engines of its violations.
Typical workflow
- Call
listPagesto determine whether the page has been tested. - If it has been tested:
- Use
listIssuesto identify reports about the page and summarize the issues reported by one report. - Use
listViolatorsto inspect elements violating rules belonging to an issue. - Use
listDiagnosesto inspect diagnoses by rule engines of violations of applicable rules by an element. - Use
getReportto retrieve an entire JSON report. - Use
requestRetestororderRetestif the latest report is obsolete and you want the page retested.
- Use
- If the page has not been tested:
- Use
requestNewTestororderNewTestif you want the page tested.
- Use
Test request and order processing
A test or retest request is reviewed by a manager. If approved, the testing is typically performed within a day.
A test or retest order is reviewed automatically and immediately. If it is approved, you get a report identifier. You can then use awaitTest, with the identifier, to await test completion, which typically takes 2 to 4 minutes, or you can later use listIssues with the identifier to check the status.
Reporting to users
When reporting test results to users:
- Do not assume a requested or ordered test or retest has produced a report until Kilotest confirms this.
- You may quote the Kilotest classification of issues into priorities, but identify any additional prioritization recommendations as your own.
- You may quote recommendations for remediation made by rule engines in diagnoses, but identify any additional remediation recommendations as your own.
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.
- yesterday First seen · 52 lines · 85 tokens per session scan A 45fcc9a23578
kilotest-overview is a skill published in the GitHub repository jrpool/kilotest (4 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 623 once invoked, about $0.0003 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 2026-10-26.
Other skills, from other repositories
a11y-ally
Use when running comprehensive WCAG accessibility audits with axe-core + pa11y + Lighthouse, generating context-aware remediation, or testing video accessibility. Supports 3-tier browser cascade with graceful degradation.
accessibility-testing
WCAG 2.2 compliance testing, screen reader validation, and inclusive design verification. Use when ensuring legal compliance (ADA, Section 508), testing for disabilities, or building accessible applications for 1 billion disabled users globally.
playwright-scanner
Internal helper: behavioral scans via Playwright for keyboard and state.
kb-github-a11y-scanner
Reference data, not a reviewer. Integrate GitHub Accessibility Scanner. Detects configuration, parses scanner issues, correlates with local scans, and tracks Copilot-assigned fixes.
kb-playwright-testing
Reference data, not a reviewer. Browser accessibility testing using Playwright and @axe-core/playwright. Keyboard scans, contrast verification, and accessibility tree snapshots.
testing-coach
How to test: screen readers, keyboard passes, automated checks and CI.