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/marchatton/agent-skills/parallel-web-toolsnpx skills add marchatton/agent-skills --skill parallel-web-toolsgit clone --depth 1 https://github.com/marchatton/agent-skillsWrote 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.
[](https://agentmods.dev/skills/marchatton/agent-skills/parallel-web-tools)<a href="https://agentmods.dev/skills/marchatton/agent-skills/parallel-web-tools"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/parallel-web-tools.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00039 | $0.00429 |
| Opus 5 | $0.00019 | $0.00215 |
| Sonnet 5 | $0.00008 | $0.00086 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
parallel-web-tools 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 4d 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.
What it actually says
parallel-web-tools
Purpose
Provide a repeatable workflow to:
- discover relevant URLs with Parallel Search
- extract clean markdown from URLs (including JS-heavy pages and PDFs) with Parallel Extract
- return objective-focused excerpts or full content depending on task
When to use
Use when asked to:
- search the web for relevant sources with an explicit objective
- extract clean markdown from one or many URLs
- do “scrape this page” but want objective-focused excerpts, not raw HTML
What this skill is not
- Not a live browser probe for computed styles or hover/focus diffs.
- For “CSS etc”, use a browser-probe lane (agent-browser / Playwright) alongside Parallel.
Required setup
- Set environment variable
PARALLEL_API_KEY. - Base URL:
https://api.parallel.ai - Headers:
x-api-key: <key>parallel-beta: search-extract-2025-10-10
Workflow
1) Decide search vs extract
- Use Search when URLs are unknown.
- Use Extract when URLs are known.
2) Search
- Provide objective and/or search_queries
- mode: one-shot | agentic | fast
- Capture url, title, publish_date (if present), excerpts
3) Extract
- Provide urls list
- objective optional (recommended)
- excerpts=true for objective-aligned snippets
- full_content=true for full markdown
4) Error handling
- Retry failures up to 2 times with backoff.
- Batch requests if rate limits appear.
Output shape recommendation
- run_metadata
- search_results (if used)
- extract_results (if used)
- errors/warnings
Use scripts/parallel_search_extract.py for a ready-to-run CLI.
What ships with it
6 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.
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.
- 4d ago First seen · 64 lines · 39 tokens per session scan A 29383b86b5e9
parallel-web-tools is a skill published in the GitHub repository marchatton/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 429 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…