spider-king

spider-king is a skill for Claude Code, Codex from Ertinox7711/SGRR-AGI-V2. It costs 136 tokens per session (7,327 once invoked), scanned A, original, MIT.

A workflow for studying how a website's client works and building a Python collector that talks to its underlying web requests instead of driving a browser. It may use a small local JavaScript helper to recreate request parameters or signatures.

In plain words
What is it for?
Use it to inspect a target site's network behavior, recover request parameters, and create browser-free Python data collectors.
Why use it?
It avoids shipping browser automation as the final collector and focuses on the requests and changing values the site actually uses.

Skill for Claude CodeCodex

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

Good fit Use it to inspect a target site's network behavior, recover request parameters, and create browser-free Python data collectors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ertinox7711/sgrr-agi-v2/spider-king
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 Ertinox7711/SGRR-AGI-V2 --skill spider-king
Clone the repo
git clone --depth 1 https://github.com/Ertinox7711/SGRR-AGI-V2

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 spider-king

README.md
[![agentmods](https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/spider-king/github.svg)](https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/spider-king)
Your own site
<a href="https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/spider-king"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/spider-king/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 spider-king

Your own site · 80×15
<a href="https://agentmods.dev/skills/ertinox7711/sgrr-agi-v2/spider-king"><img src="https://agentmods.dev/badge/skills/ertinox7711/sgrr-agi-v2/spider-king.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,327 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 $0.00136 $0.07327
Opus 5 $0.00068 $0.03664
Sonnet 5 $0.00027 $0.01465
Haiku 4.5 $0.00014 $0.00733

Measured 3d ago against content hash 2a9d258c777f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

spider-king 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.

skills/spider-king/SKILL.md · 775 lines

How it starts

The opening of the file, as written. The whole thing — 775 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spider King

Role

Turn hostile web clients into stable protocol collectors.

This skill is not a browser automation skill. This skill is a protocol recovery skill.

Default posture:

  1. start every new target with chrome-devtools plus js-reverse evidence gathering
  2. find the real request
  3. identify the true changing state
  4. rebuild that state offline
  5. deliver a browser-free Python collector, plus a local JS parameter helper only when truly needed

Non-Negotiables

  • Final delivery must be pure protocol: raw HTTP plus local signer, local decoder, or local bootstrap helper only.
  • Every new target must be analyzed first with both chrome-devtools and js-reverse before writing the final collector.
  • Do not ship Playwright, Selenium, CDP page-driving, or submit-through-browser flows as the solution.
  • Final delivery must run fully outside the browser: Python crawler scripts for collection, plus a local JS helper only for parameter, sign, token, or cookie reconstruction when Python porting is not yet the safest choice.
  • Prefer Python for the collector and orchestration.
  • Only keep a tiny isolated JS or WASM helper when a verified Python port is not yet cheaper, safer, or faster to maintain.
  • Any JS helper must run locally without page driving, document, window, manual clicks, browser profiles, or hidden browser dependencies.
  • If browser tooling is used at all, use it only for recon and evidence gathering, never as a hidden dependency in the final collector.
  • Automation is forbidden as the final answer, forbidden as a fallback answer, and forbidden as a disguised "temporary" delivery path.
  • Recover one stable request before scaling pagination, concurrency, or submission.
  • Every conclusion must be backed by artifacts: request samples, fixed-input helper outputs, cookies, headers, and replay proof.
  • Stay in one execution loop until you reach protocol delivery or hit a real external blocker.

Startup Gate

Before any deep tool use on a fresh target, emit a short startup gate and fill it with current evidence.

Read the full file on GitHub · 775 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. 3d ago First seen · 775 lines · 136 tokens per session scan A 2a9d258c777f

Subscribe to this mod's changes

spider-king is a skill published in the GitHub repository Ertinox7711/SGRR-AGI-V2 (1 stars, last pushed 4d ago), licensed MIT. It adds 136 tokens to every session and 7,327 once invoked, about $0.0007 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 2026-09-09.