octocode-scraping

octocode-scraping is a skill for Claude Code, Codex from bgauryy/octocode. It costs 89 tokens per session (1,355 once invoked), scanned A, original, MIT.

A process for collecting public web pages into a local, searchable collection with source details. It can crawl a URL or documentation site, extract structured information, and recover from blocked or incomplete pages within defined limits.

In plain words
What is it for?
It is for scraping documentation, pricing, product details, and tables; building a cited web-content collection; searching saved pages; and diagnosing access or page-quality problems.
Why use it?
It keeps research evidence available locally so answers can be checked against saved pages instead of repeatedly fetching the same content. It also defines when to stop or ask for approval.

Skill for Claude CodeCodex

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

Good fit It is for scraping documentation, pricing, product details, and tables; building a cited web-content collection; searching saved pages; and diagnosing access or page-quality problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bgauryy/octocode/octocode-scraping
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 bgauryy/octocode --skill octocode-scraping
Clone the repo
git clone --depth 1 https://github.com/bgauryy/octocode

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 octocode-scraping

README.md
[![agentmods](https://agentmods.dev/badge/skills/bgauryy/octocode/octocode-scraping/github.svg)](https://agentmods.dev/skills/bgauryy/octocode/octocode-scraping)
Your own site
<a href="https://agentmods.dev/skills/bgauryy/octocode/octocode-scraping"><img src="https://agentmods.dev/badge/skills/bgauryy/octocode/octocode-scraping/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 octocode-scraping

Your own site · 80×15
<a href="https://agentmods.dev/skills/bgauryy/octocode/octocode-scraping"><img src="https://agentmods.dev/badge/skills/bgauryy/octocode/octocode-scraping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,355 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00089 $0.01355
Opus 5 $0.00044 $0.00678
Sonnet 5 $0.00018 $0.00271
Haiku 4.5 $0.00009 $0.00136

Measured 12d ago against content hash 19c2243e3b32, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

octocode-scraping 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 12d ago.

The scan reads SKILL.md. This mod also ships 23 executable files (scripts/corpus-find.mjs, scripts/corpus-inspect.mjs, scripts/corpus-run.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/octocode-scraping/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Octocode Scraping

Flow: FRAME → POLICY → ROUTE → FETCH → CORPUS → SEARCH → CITE → RECOVER.

FRAME before the first fetch: fix target URL/domain, goal, depth, and output shape — vague ask → references/user-inputs.md.

Defaults: one public URL, --mode html, omit --provider (keyless cdpdirect), session .octocode/tmp/scrape/{sessionId}, compact stdout. Search corpus before refetch. Live interaction → chrome-devtools on one port, then har-ingest + corpus-run into the same session. Ask before auth, hosted spend, crawl widen, CAPTCHA/MFA, destructive actions. Cite paths + URL metadata — not raw dumps.

Stop when: two same-class failures (report evidence, route tried, sanitized status, next approval); hosted 403 (wrong key or credits gone — status only, no retry); CAPTCHA/MFA, auth wall, or cookie/profile transfer needed; still blocked after one cdp try (ask before --provider scrapingant); personal data, form submits, purchases, sends, deletes, or account changes in scope; the saved corpus already proves the claim (cite it, do not refetch); crawl widen before reports/summary.md is useful. Recovery table: references/failure-recovery.md.

Route (pick one)

Need Do Skip
Vague scrape --mode html, omit --provider markdown / auto hosted
See auto pick scripts/provider-check.mjs guessing
Fetch/crawl scripts/fetch.mjs deprecated scrapingant-fetch
Corpus on disk corpus-inspect → find helpers → corpus-run blind refetch
Live click/DOM/auth chrome-devtools --provider cdp alone for interaction
Page health chrome measure + measure-query hosted scrape for scores
CDP → corpus scripts/har-ingest.mjs --from-cdp-dir new sessionId
Prove field scripts/corpus-run.mjs --regex|--script reopen browser
Still blocked evidence + ask → --provider scrapingant silent spend

Scripts (Node, no install; every one takes --help)

When Run
fetch / crawl / extract a URL — the owner of every network call scripts/fetch.mjs --url <u> [--mode html] [--crawl --same-domain --max-pages <n>] [--no-raw]
want the fetch plus an immediate corpus brief in one shot scripts/fetch-and-brief.mjs --url <u> (wraps fetch.mjscorpus-inspect.mjs)
before routing or hosted spend: which provider auto-wins, credits left scripts/provider-check.mjs [--provider <p>], scripts/provider-usage.mjs — sanitized, never prints the key
read a saved session first, then search it scripts/corpus-inspect.mjs --session-dir <d> [--page <n>], then scripts/corpus-find.mjs --session-dir <d> --query <t>
pull static DOM, assets, or graph paths out of the corpus (live DOM → chrome-devtools) scripts/dom-find.mjs --kind form/button/table, scripts/resource-list.mjs --kind asset/external, scripts/graph-navigate.mjs --from <nodeId> — each with --session-dir <d>
prove one field locally instead of reopening a browser scripts/corpus-run.mjs --session-dir <d> --roots cdp,extracts --regex <re> (or --script <file>, --concat-parts)
bridge chrome-devtools artifacts into this session, or hand a packet back scripts/har-ingest.mjs --session-dir <d> --from-cdp-dir <run>; reverse with --export-packet
need field names before an extraction scripts/schema-helper.mjs --intent "extract pricing and features"
an old transcript uses the legacy names deprecated shims scripts/scrapingant-fetch.mjs, scripts/scrapingant-check.mjs, scripts/scrapingant-usage.mjs forward to fetch.mjs / provider-check.mjs / provider-usage.mjs — call the new names
editing or extending a script shared modules in scripts/lib/ (providers registry, client fetch, corpus, analyzers, extractors, text, args, bridge); env/key resolution vendored in scripts/octocode-config.mjs; JSON contracts in scripts/schemas/

Read the full file on GitHub · 59 lines

Files

What ships with it

40 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 59 lines · 89 tokens per session scan A 19c2243e3b32

Subscribe to this mod's changes

octocode-scraping is a skill published in the GitHub repository bgauryy/octocode (932 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 1,355 once invoked, about $0.0004 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 2026-08-30.