scraping-at-scale

scraping-at-scale is a skill for Claude Code from yale-som-hpc/claude-code-marketplace. It costs 82 tokens per session (3,235 once invoked), scanned C, original, Unlicense.

Guidance for storing and managing very large web crawls on Yale SOM's shared computing cluster. It separates the crawl catalog, downloaded page contents, and record of fetch attempts.

In plain words
What is it for?
Crawling tens of thousands of pages or more, storing HTML or JSON responses, re-parsing saved pages, and tracking which URLs succeeded or failed.
Why use it?
It keeps crawls resumable and avoids creating millions of small files that slow the cluster's shared storage system.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the hpc plugin — 23 skills, 3 commands shipped together

Good fit Crawling tens of thousands of pages or more, storing HTML or JSON responses, re-parsing saved pages, and tracking which URLs succeeded or failed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yale-som-hpc/claude-code-marketplace/scraping-at-scale
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 yale-som-hpc/claude-code-marketplace --skill scraping-at-scale
Clone the repo
git clone --depth 1 https://github.com/yale-som-hpc/claude-code-marketplace

Made for: Claude Code.

Or install hpc, the plugin that ships this one along with the rest of its 23 skills, 3 commands.

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 scraping-at-scale

README.md
[![agentmods](https://agentmods.dev/badge/skills/yale-som-hpc/claude-code-marketplace/scraping-at-scale/github.svg)](https://agentmods.dev/skills/yale-som-hpc/claude-code-marketplace/scraping-at-scale)
Your own site
<a href="https://agentmods.dev/skills/yale-som-hpc/claude-code-marketplace/scraping-at-scale"><img src="https://agentmods.dev/badge/skills/yale-som-hpc/claude-code-marketplace/scraping-at-scale/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 scraping-at-scale

Your own site · 80×15
<a href="https://agentmods.dev/skills/yale-som-hpc/claude-code-marketplace/scraping-at-scale"><img src="https://agentmods.dev/badge/skills/yale-som-hpc/claude-code-marketplace/scraping-at-scale.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,235 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00082 $0.03235
Opus 5 $0.00041 $0.01618
Sonnet 5 $0.00016 $0.00647
Haiku 4.5 $0.00008 $0.00324

Measured 11d ago against content hash f6c71963f7c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

scraping-at-scale scanned grade C with 2 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 11d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

trap 'rm -rf "$workdir"' EXIT

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

body, headers = fetch(url) # your HTTP layer (see acquiring-data)
plugins/hpc/skills/scraping-at-scale/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scraping at Scale

Rule: for a large crawl, separate the catalog (what's cached) from the bodies (the data) from the action log (what the run did). Make the catalog durable on GPFS so the job is resumable, and never materialize a million loose files.

This is the heavy machinery for crawls of tens of thousands of pages or more. For the common case (WRDS, a few API pulls, credentials, a request-hash cache), use acquiring data instead — most data work never needs what's here.

Three separate stores

data/raw_html/<aa>/<key>.html   # bodies, sharded by 2-char hash prefix
data/raw_json/<aa>/<key>.json
data/derived/                   # parsed outputs
data/metadata.db                # catalog: SQLite, one row per stored artifact
data/fetch_log.jsonl            # optional: JSONL, one row per fetch attempt

Save bodies under raw, parse separately into derived — if parsing changes, re-parse without re-fetching. Then keep two records that answer different questions:

  1. Catalog (metadata.db, SQLite). One canonical row per stored artifact, keyed by key: url, final_url, status, content_type, bytes, etag, last_modified, fetched_at. UPSERT on each success — a 304 revalidation just updates last_modified/fetched_at without duplicate rows. Answers "what's in the cache?"
  2. Action log (fetch_log.jsonl, optional). Append-only, one row per attempt: ts, url, attempt, outcome (ok/cache_hit/retry/error), status, key, error. Answers "what did the scraper do this run?" — including failures that produced no body.

Different shapes, different formats: the catalog has one-row-per-key identity, lookup, and updates (SQLite); the log is append-only and read as a stream (JSONL, safe to multi-write under O_APPEND).

Use WAL for the catalog. SQLite's default journal (DELETE) serializes readers and writers — a DuckDB query during a scrape blocks the next upsert. WAL gives concurrent reads + serialized writes, halves per-commit fsync, and with synchronous = NORMAL is durable (a crash loses at most the last in-flight transaction, never corrupts). The helper below sets it up.

Read the full file on GitHub · 232 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. 11d ago First seen · 232 lines · 82 tokens per session scan C f6c71963f7c5

Subscribe to this mod's changes

scraping-at-scale is a skill published in the GitHub repository yale-som-hpc/claude-code-marketplace (5 stars, last pushed 2mo ago), licensed Unlicense. It adds 82 tokens to every session and 3,235 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

create-pr

Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.

prisma/orm · 47 tokens

schema-exploration

Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.

langchain-ai/deepagents · 57 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

supabase

Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…

PentesterFlow/agent · 120 tokens

nornicdb-cypher-queries

Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.

orneryd/NornicDB · 79 tokens

dsql

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…

awslabs/agent-plugins · 229 tokens