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 skills/parallel-web/parallel-cursor-plugin/parallel-web-extractnpx skills add parallel-web/parallel-cursor-plugin --skill parallel-web-extractgit clone --depth 1 https://github.com/parallel-web/parallel-cursor-pluginWhat 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 | $0.00042 | $0.00680 |
| Opus 5 | $0.00021 | $0.00340 |
| Sonnet 5 | $0.00008 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
parallel-web-extract 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
URL Extraction
Extract content from: $ARGUMENTS
Command
Choose a short, descriptive filename based on the URL or content (e.g., vespa-docs, react-hooks-api). Use lowercase with hyphens, no spaces. Substitute it into the command inline — $FILENAME is a placeholder, not a shell variable.
parallel-cli extract "$ARGUMENTS" --json -o "/tmp/$FILENAME.json"
Concrete example:
parallel-cli extract "https://docs.parallel.ai" --json -o "/tmp/parallel-docs.json"
Note: -o always saves JSON. The extension must be .json.
Options if needed:
--objective "focus area"to focus extraction on a specific goal (also silences the "neither objective nor search_queries" warning that V1 emits when neither is set)-q "keyword"(repeatable) to prioritize keywords in excerpts--full-contentto include the complete page body (for long articles, PDFs, or when excerpts may not capture what you need)--full-content-max-chars Nto cap full-content size per result--no-excerptsto strip excerpts when you only want full content
Handling failed extractions
If the response has an errors field, an empty results array, or a 404/timeout for the URL, do NOT fabricate content. Tell the user the extraction failed, surface the upstream status, and suggest:
- Verifying the URL (the page may have moved)
- Retrying with
--full-contentif excerpts came back empty but the page exists - Using
parallel-cli searchto locate the current URL if the page was renamed
Response format
Return content as:
Then the extracted content verbatim, with these rules:
- Keep content verbatim - do not paraphrase or summarize
- Parse lists exhaustively - extract EVERY numbered/bulleted item
- Strip only obvious noise: nav menus, footers, ads
- Preserve all facts, names, numbers, dates, quotes
After the response, mention the output file path (/tmp/$FILENAME.json) so the user knows it's available for follow-up questions.
If the parallel-cli binary is not installed
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 · 65 lines · 42 tokens per session scan A dffc4d3ab2a7
parallel-web-extract is a skill published in the GitHub repository parallel-web/parallel-cursor-plugin (3 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 680 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…