agentmods.dev

xray-suite

xray-suite is a skill for Claude Code, Codex from Roshu18/bearstrike-ai. It costs 25 tokens per session (703 once invoked), scanned A, original, MIT.

A playbook for using web security scanners, a crawler, and a headless browser, which is a browser controlled by software without a visible window. It describes a cautious order of checks and how to keep requests limited.

In plain words
What is it for?
Use it to profile web targets, discover dynamic endpoints, run focused web and service scans, inspect subdomains, and render pages for testing when you have permission.
Why use it?
It helps structure web security testing while reducing unnecessary traffic and the risk of overwhelming a target. It also explains how to respond when a web application firewall blocks or limits scans.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 8repo 7mo ago A scan 25 tokens original MIT

Good fit Use it to profile web targets, discover dynamic endpoints, run focused web and service scans, inspect subdomains, and render pages for testing when you have permission.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/roshu18/bearstrike-ai/xray-suite
View source ↗ Roshu18/bearstrike-ai
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.

Any agent
npx skills add Roshu18/bearstrike-ai --skill xray-suite
Clone the repo
git clone --depth 1 https://github.com/Roshu18/bearstrike-ai

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for xray-suite

README.md
[![agentmods](https://agentmods.dev/badge/skills/roshu18/bearstrike-ai/xray-suite/github.svg)](https://agentmods.dev/skills/roshu18/bearstrike-ai/xray-suite)
Your own site
<a href="https://agentmods.dev/skills/roshu18/bearstrike-ai/xray-suite"><img src="https://agentmods.dev/badge/skills/roshu18/bearstrike-ai/xray-suite/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.

agentmods 80×15 button for xray-suite

Your own site · 80×15
<a href="https://agentmods.dev/skills/roshu18/bearstrike-ai/xray-suite"><img src="https://agentmods.dev/badge/skills/roshu18/bearstrike-ai/xray-suite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 703 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00025 $0.00703
Opus 5.5 $0.00010 $0.00281
Sonnet 5.5 $0.00005 $0.00141
Haiku 4.5 $0.00003 $0.00070

Measured 2mo ago against content hash a841fea97bdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

xray-suite 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 2mo 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.

skills/xray-suite/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

xray-suite

Read this skill before using any xray-suite-* tool.

Components

  1. xray-suite-webscan
  2. xray-suite-servicescan
  3. xray-suite-subdomain
  4. xray-suite-crawlergo
  5. xray-suite-headless-browser

Dynamic binary resolution

The bridge script tools/xray_suite_tools.py resolves tools in this order:

  1. Project-local bundles under tools/bin/
  2. Windows installed binaries (when available)
  3. Linux PATH binaries (xray, crawlergo, chrome-headless-shell, google-chrome, chromium)

Safe usage policy

  1. Start with low-noise recon and rendering first.
  2. Use xray-suite-headless-browser and xray-suite-crawlergo before full webscan.
  3. Keep scan scope narrow (specific hosts/URLs), not broad wildcards.
  4. Respect WAF signals and reduce intensity when blocks appear.
  5. Avoid aggressive brute-force against production targets without explicit authorization.
  1. Target profiling: wafw00f, whatweb, httpx
  2. Dynamic endpoint discovery: xray-suite-headless-browser, xray-suite-crawlergo
  3. Focused vulnerability scan: xray-suite-webscan
  4. Service checks where relevant: xray-suite-servicescan
  5. Optional domain expansion: xray-suite-subdomain (license/build dependent)

No-ban scanning defaults

Bridge config uses conservative defaults in tools/xray_suite/config.yaml:

  1. parallel: 10
  2. http.max_qps: 30
  3. http.max_conns_per_host: 20

When a target is sensitive or starts rate-limiting:

  1. Reduce target scope to a single URL/path.
  2. Lower concurrency/QPS further.
  3. Pause between major scan phases.

Plugin policy

The project config keeps these enabled:

  1. plugins.brute-force.enabled: true
  2. plugins.thinkphp.enabled: true

Runtime note:

  • Some community builds can still disable certain plugins at runtime due licensing. Treat runtime output as authoritative.

False-positive controls

  1. Re-run suspected findings at least twice.
  2. Confirm differences between benign and malicious payload behavior.
  3. Validate real impact (not only reflected errors).
  4. Exclude WAF block pages, CDN errors, and transient backend failures.
  5. Save deterministic reproduction evidence for reporting.

Read the full file on GitHub · 81 lines

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. 2mo ago First seen · 81 lines · 25 tokens per session scan A a841fea97bdb

Subscribe to this mod's changes

xray-suite is a skill published in the GitHub repository Roshu18/bearstrike-ai (8 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 703 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.

LLMSecurityai-cybersecurityai-hackingkali-linuxmcpmcp-server
Related

Other skills, from other repositories

gentech-blockrun

GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Covers daily usage patterns, cost-optimized workflows, multi-tool pipelines, and reliable error handling for BlockRun's full toolset.

BlockRunAI/blockrun-mcp · 46 tokens

portainer-mcp-hygiene

How to drive the Portainer MCP server's tools correctly — both reading and mutating. Reading: project responses with select (JMESPath), where the heavy fields live (snapshots, status blocks, managed fields), how to handle non-JSON Docker/K8s proxy endpoints (container and pod logs, stats, exec), and how to interpret…

portainer/portainer-mcp · 315 tokens

hmem-release

Pre-publish checklist for hmem: skills synced, version bumped, tests green, nothing forgotten. Use before npm publish or when the user says 'release', 'publish', 'push a release', or 'neue Version'.

Bumblebiber/hmem · 50 tokens

disease-analysis

Run a multi-scale disease pathophysiology analysis — molecular defects through to clinical symptoms — using TogoMCP (RDF Portal SPARQL), TogoID ID conversion, OLS4, and PubMed. Use whenever the user asks to "analyze a disease", build a disease mechanism model, find disease-associated proteins/pathways/drugs, map a…

dbcls/togomcp · 149 tokens

research-article-analysis

Systematically validate a research article's claims against TogoMCP RDF databases — molecular formulas, reaction equations, pathways, protein function, GO definitions — instead of trusting the paper's text or keyword-search snippets. Use whenever the user asks to "analyze this paper/article", fact-check or validate a…

dbcls/togomcp · 147 tokens

index-advisor

Recommend which indexes to add or drop for a connection, using DeepSQL's workload-weighted advisor, and optionally dry-run/apply them.

DeepSQLAI/deepsql · 32 tokens