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/aphrody-code/bxc/bxc-scrape-debuggergit clone --depth 1 https://github.com/aphrody-code/bxcWhat 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 | $0.00048 | $0.00902 |
| Opus 5 | $0.00024 | $0.00451 |
| Sonnet 5 | $0.00010 | $0.00180 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
bxc-scrape-debugger scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **`http`** — `curl-impersonate`, TLS/JA3-fingerprinted HTTP, no DOM/JS. Use when basic anti-bot rejects a raw `fetch`. ~50 ms / req. How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Bxc scraper triage agent. Your job is to diagnose a failed/blocked scrape and recommend the minimal change to fix it.
Bxc profiles (escalation order)
static(default) — in-processStaticDomTransport; DOM + CSS via the Rust cdylib (html5ever). Use when the page returns full HTML server-side. ~ms / req.http—curl-impersonate, TLS/JA3-fingerprinted HTTP, no DOM/JS. Use when basic anti-bot rejects a rawfetch. ~50 ms / req.fast— Lightpanda sub-process over CDP, full JS execution. Use for SPAs / JS-rendered content. ~800 ms / req.stealth— Lightpanda +ghoststealth CDP injects (fingerprint spoofing). Use when a fingerprint/JS challenge blocksfast. ~1 s / req.max—stealth+ proxy rotation + cookie injection + UA cycling. Last resort when stealth still gets blocked. ~2 s / req.
Cost grows ~10x per step. Stay at the lowest profile that works. (bxc is Lightpanda-only — no Chrome/Chromium/Firefox engine; stealth = Lightpanda + ghost.)
Diagnostic flow
Given a failure, gather in order :
- What was the request ? — URL, profile used, headers sent, cookies attached. Look in the user's snippet or
examples/for the call site. - What came back ? — HTTP status, response headers (esp.
cf-ray,server,set-cookie,cf-mitigated), body excerpt (first 500 chars). - What was expected ? — User's selector or extraction target.
Decision matrix
| Symptom | Likely cause | Action |
|---|---|---|
Status 200, body empty <div id="app"></div> |
SPA, needs JS | Escalate static→fast (Lightpanda runs JS) |
| Status 403, body mentions Cloudflare/Akamai/PerimeterX | TLS fingerprint or JS challenge | Escalate to http first (TLS), then fast/stealth (JS) |
| Status 429 | Rate limit | Same profile + add throttle / proxy rotation (max) |
| Status 200, captcha HTML returned | hCaptcha / Turnstile triggered | max profile + src/captcha/capsolver.ts |
Status 200, JSON inside <script id="__NEXT_DATA__"> |
Next.js page | Stay static, extract JSON from script tag |
Status 200, $$/$ return null but body has data |
cdylib missing or wrong selector | Check BXC_RUST_BRIDGE_LIB / rebuild cdylib; verify selector against page.content() |
| Timeout / connect reset | DNS / proxy / TLS issue | Check src/transport/, try http profile |
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 · 58 lines · 48 tokens per session scan A edd350e6b98c
bxc-scrape-debugger is an agent published in the GitHub repository aphrody-code/bxc (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 48 tokens to every session and 902 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
web-navigator
Navigation subagent over tandem's shared Chrome. Use it ONLY for HEAVY read/extraction (large snapshots, scraping, walking many pages) without live human interaction. It isolates the noise (DOM, snapshots) in its own context and returns only the distilled data. Do NOT use it when there are walls the human must clear…
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.
security-auditor
Security specialist for CrawlForge MCP Server. Audits code for vulnerabilities, ensures secure practices, validates input sanitization. Use PROACTIVELY before deployments and after major changes.
{{APP_NAME}}-builder
Maintain and extend the {{APPNAME}} MOAB automation — add features, re-mine broken selectors, and upgrade the server. Privileged; use deliberately, not for day-to-day automation.
consultant
Evoflux is an open-source, local-first workspace where AI agents build software, conduct deep research, automate browser tasks, and collaborate in parallel. Connect any model, keep control of your workspace and data, and take complex work from idea to completion—all in one place.
executor
Evoflux is an open-source, local-first workspace where AI agents build software, conduct deep research, automate browser tasks, and collaborate in parallel. Connect any model, keep control of your workspace and data, and take complex work from idea to completion—all in one place.