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 billy-enrizky/openbrowser-ai --skill accessibility-auditgit clone --depth 1 https://github.com/billy-enrizky/openbrowser-aiWrote 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/billy-enrizky/openbrowser-ai/accessibility-audit)<a href="https://agentmods.dev/skills/billy-enrizky/openbrowser-ai/accessibility-audit"><img src="https://agentmods.dev/badge/skills/billy-enrizky/openbrowser-ai/accessibility-audit/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/billy-enrizky/openbrowser-ai/accessibility-audit"><img src="https://agentmods.dev/badge/skills/billy-enrizky/openbrowser-ai/accessibility-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 Tool Misuse · line 31 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- high YARA Match · line 397 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
- medium Rogue Agent · line 8 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- low Supply Chain · line 31 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00070 | $0.03703 |
| Opus 5 | $0.00035 | $0.01852 |
| Sonnet 5 | $0.00014 | $0.00741 |
| Haiku 4.5 | $0.00007 | $0.00370 |
Grade B, and why
accessibility-audit scanned grade B with 2 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 9d 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(openbrowser-ai:*) Bash(curl:*) Bash(uv:*) Bash(irm:*) Read Write How it starts
The opening of the file, as written. The whole thing — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Audit
Audit web pages for accessibility issues following WCAG 2.1 guidelines using Python code execution. Checks heading structure, form labels, image alt text, ARIA attributes, landmark regions, and keyboard navigation.
All code runs via openbrowser-ai -c. The daemon starts automatically and persists variables across calls. All browser functions are async -- use await.
The CLI daemon also persists cookies and login state in ~/.config/openbrowser/profiles/daemon/storage_state.json, so authenticated sessions can be reused across later runs.
Setup
Before running, verify openbrowser-ai is installed:
openbrowser-ai --help
If not found, install:
# macOS/Linux
curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh
# Windows (PowerShell)
irm https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.ps1 | iex
Workflow
Step 1 -- Navigate and initialize audit
openbrowser-ai -c - <<'EOF'
await navigate("https://example.com")
state = await browser.get_browser_state_summary()
print(f"Auditing: {state.title} ({state.url})")
# Store all findings
audit = {
"url": state.url,
"title": state.title,
"issues": [],
"checks": {}
}
EOF
Step 2 -- Check heading structure
openbrowser-ai -c - <<'EOF'
headings_result = await evaluate("""
(function(){
const headings = Array.from(document.querySelectorAll("h1,h2,h3,h4,h5,h6"));
const issues = [];
let prevLevel = 0;
const h1Count = headings.filter(h => h.tagName === "H1").length;
if (h1Count === 0) issues.push("No h1 element found");
if (h1Count > 1) issues.push("Multiple h1 elements: " + h1Count);
headings.forEach(h => {
const level = parseInt(h.tagName[1]);
if (prevLevel > 0 && level > prevLevel + 1)
issues.push("Skipped level: h" + prevLevel + " -> h" + level + " (\"" + h.textContent.trim().substring(0, 50) + "\")");
if (!h.textContent.trim())
issues.push("Empty heading: " + h.tagName);
prevLevel = level;
});
return {
total: headings.length,
h1Count,
hierarchy: headings.map(h => ({ tag: h.tagName, text: h.textContent.trim().substring(0, 80) })),
issues
};
})()
""")
audit["checks"]["headings"] = headings_result
for issue in headings_result.get("issues", []):
audit["issues"].append({"check": "headings", "wcag": "1.3.1", "issue": issue})
print(f"[HEADINGS] {issue}")
if not headings_result.get("issues"):
print("[HEADINGS] PASS")
EOF
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.
- 9d ago First seen · 411 lines · 70 tokens per session scan B e6bed378299b
accessibility-audit is a skill published in the GitHub repository billy-enrizky/openbrowser-ai (241 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 3,703 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
compiler-port
Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.
verify
Build, launch, drive, and screenshot the OpenNOW Electron settings UI on Windows.
break
Renders a component you choose in every state and scenario on a temporary page and stress tests it.
visual-qa
MUST USE after building/changing any UI or when asked whether a page, component, or TUI looks right. Rigorous visual QA across web/page and terminal UIs. Prefer browser:control-in-app-browser for unauthenticated browser/page QA in Codex, then Playwright/agent-browser/dev-browser. Captures screenshot/TUI evidence with…
menu-testing-ssr
Server rendering and testing for react-horizontal-scrolling-menu: the library is client-only ('use client' required in React Server Components, else "createContext is not a function"), SSR first paint is controlled by the useIsVisible defaultValue argument (canonical ('first', true) / ('last', false))…