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 agentmods add agents/tyrusrc/praetor/browser-agentgit clone --depth 1 https://github.com/TyrusRC/praetorWhat 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 | $0.00032 | $0.00547 |
| Opus 5 | $0.00016 | $0.00273 |
| Sonnet 5 | $0.00006 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00055 |
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 3d 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.
What it actually says
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 statebrowser_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
}
Constraints
- Max 1 browser-agent in parallel. Orchestrator MUST NOT dispatch a second.
- Never follow out-of-scope redirects (Rule 2).
- Call
browser_closeeven on early termination.
Status Report (return this JSON)
Your final output is one status object per AGENTS.md (Agent Status Schema section) — no surrounding prose. The new_endpoints list stays in ## Returns:
{"agent":"browser-agent","domain":"<domain>","phase":"crawl","status":"done","findings_confirmed":0,"findings_suspected":0,"coverage_note":"<N pages, N xhr, N forms; proxy history populated>","next_action":"<e.g. dispatch js-analyst on captured bundles>","blockers":[]}
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.
- 3d ago First seen · 57 lines · 32 tokens per session scan A 261b15e3b92a
browser-agent is an agent published in the GitHub repository TyrusRC/praetor (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 32 tokens to every session and 547 once invoked, about $0.0002 per session on Opus 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
senior-pentester
20+ year offensive security reviewer. Receives one logical firewall's normalized ruleset (already through deterministic detectors) and flags semantic concerns detectors can't catch — business-logic gaps, trust-boundary violations, unusual service combos. 2-4 instances dispatched in parallel during /launch.
cto-reviewer
Technical truth gate. Re-derives each finding's claim from the parsed rule AST and returns yes/no/uncertain. Uncertain findings route to held/ for human reviewer.
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-reviewer
Editorial gate. Final pass on phrasing, framework-citation-version accuracy, cross-finding consistency. Flags (never blocks) findings that need author attention.
agent-dynamic-tester
Role brief for the dynamic-tester agent — performs runtime / negative testing (Perform / Test methods) against an authorized running instance for PCI SSS v2.0 dynamic Test Requirements, capturing dynamicobservation evidence. When no running instance is authorized, the requirement is REQUIRESMANUALREVIEW, never a faked…