browser-agent

A headless-browser agent for crawling websites that rely on JavaScript, including single-page applications, and recording the routes and API requests it reaches in Burp Proxy.

In plain words
What is it for?
It helps explore in-scope domains, interact with pages and forms using test values, and collect dynamic routes and XHR/API calls for later analysis.
Why use it?
It finds pages and network requests that a simple HTTP crawler may miss because they appear only after clicks, form input, or other browser actions.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/tyrusrc/praetor/browser-agent
Clone the repo
git clone --depth 1 https://github.com/TyrusRC/praetor

Made for: Claude Code.

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 547 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 261b15e3b92a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/agents/browser-agent.md · 57 lines

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, default https://<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

  1. check_scope(entry_url) — abort if out of scope
  2. browser_navigate(entry_url) — initial load
  3. browser_get_page_info — read DOM state
  4. browser_interact_all with action_budget — auto-click, auto-fill (per page-bounded budget)
  5. On forms: browser_fill with test values; browser_submit_form
  6. Capture: every interaction populates Proxy history (visible to subsequent analysis tools)
  7. browser_close at 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_close even 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":[]}
Changes

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.

  1. 3d ago First seen · 57 lines · 32 tokens per session scan A 261b15e3b92a

Subscribe to this mod's changes

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.

Related

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.

transilienceai/communitytools · 62 tokens

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.

transilienceai/communitytools · 40 tokens

ciso-reviewer

Business-impact gate. Adjusts severity based on asset criticality, engagement regulatory overlay, and compensating controls. Does NOT veto findings.

transilienceai/communitytools · 32 tokens

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.

transilienceai/communitytools · 41 tokens

qa-reviewer

Editorial gate. Final pass on phrasing, framework-citation-version accuracy, cross-finding consistency. Flags (never blocks) findings that need author attention.

transilienceai/communitytools · 35 tokens

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…

transilienceai/communitytools · 73 tokens