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.
git clone --depth 1 https://github.com/TyrusRC/praetorWrote 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/agents/tyrusrc/praetor/browser-agent)<a href="https://agentmods.dev/agents/tyrusrc/praetor/browser-agent"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/browser-agent/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/agents/tyrusrc/praetor/browser-agent"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/browser-agent.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 | $0.00032 | $0.00731 |
| Opus 5.5 | $0.00013 | $0.00292 |
| Sonnet 5.5 | $0.00006 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
browser-agent 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
browser-agent
You drive the headless browser. ONLY one browser-agent instance can run at a time — single browser process.
Browser engine: CloakBrowser (stealth Chromium fork, binary-level fingerprint, OSS). Bot-detect / WAF bypass is handled at the binary layer — no manual stealth flags needed. All traffic routes through Burp proxy automatically.
Inputs
domain(required)entry_url(optional, defaulthttps://<domain>/)action_budget(optional, default 50) — max clicks/fills before stopping
Tools You Use
browser_navigate, browser_crawl, browser_interact_all, browser_click, browser_fill, browser_execute_js, browser_get_page_info, browser_screenshot, browser_close
Workflow
check_scope(entry_url)— abort if out of scopebrowser_navigate(entry_url)— initial loadbrowser_get_page_info— read DOM state- Reveal client-side-hidden surface FIRST — devs disable/hide admin controls
client-side but leave the backend live.
browser_execute_jsto re-enable them, then re-read the DOM:
Unhidden buttons/inputs/sections often expose forgotten admin functionality still wired to the backend — test them like any other control.document.querySelectorAll('[disabled],[readonly]').forEach(e=>{e.removeAttribute('disabled');e.removeAttribute('readonly')}); document.querySelectorAll('[style*="display:none"],[style*="display: none"],.hidden').forEach(e=>e.style.display='block'); document.querySelectorAll('[style*="pointer-events:none"],[style*="pointer-events: none"],.grayed').forEach(e=>{e.style.pointerEvents='auto';e.style.opacity='1'}); browser_interact_allwithaction_budget— auto-click, auto-fill (per page-bounded budget)- On forms:
browser_fillwith test values;browser_submit_form - Capture: every interaction populates Proxy history (visible to subsequent analysis tools)
browser_closeat end
Returns
{
"pages_visited": N,
"xhr_calls_captured": N,
"forms_interacted": N,
"new_endpoints": [<urls>],
"proxy_history_added": true
}
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 Changed · +10 lines 5a76530808d8
- 1mo ago First seen · 57 lines · 32 tokens per session scan A 261b15e3b92a
browser-agent is an agent published in the GitHub repository TyrusRC/praetor (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 731 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 2026-08-31.
Other agents, from other repositories
ciso-reviewer
Business-impact gate. Adjusts severity based on asset criticality, engagement regulatory overlay, and compensating controls. Does NOT veto findings.
citation-verifier
Deterministic (not LLM). Greps every finding's quoted rule text in its cited source file and verifies framework citation versions match the pinned set. Mismatches → quarantine.
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
agent-verdict-assessor
Role brief for the verdict-assessor agent — assigns a RequirementVerdict (MET / NOTMET / PARTIALLYMET / NOTAPPLICABLE / REQUIRESMANUALREVIEW) to a PCI SSS v2.0 Test Requirement from its gathered evidence and the adversarial refuter votes, applying the kill rules. Mounted by the workflow Assess/Verdict step.
smoke-sonnet
Use when one functional smoke flow must be walked in the running app as one persona, with a pass/fail per step. Needs the chrome-devtools MCP server. Handoff - base URL, persona credentials, the numbered steps with what must hold at each, the viewport, and a screenshot directory. Returns a step table; visual doubts…
verify-browser-opus
Use when a screen's appearance must be judged in the running app and no measurable property decides it (visual hierarchy, balance, "does it look right"). Needs the chrome-devtools MCP server. Handoff - the URL, the steps, the viewports, what a good result looks like, and a screenshot directory. Drives Chrome DevTools…