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-deep-researchnpx skills add parallel-web/parallel-cursor-plugin --skill parallel-deep-researchgit 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 | $0.00076 | $0.01528 |
| Opus 5 | $0.00038 | $0.00764 |
| Sonnet 5 | $0.00015 | $0.00306 |
| Haiku 4.5 | $0.00008 | $0.00153 |
Grade A, and why
parallel-deep-research 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Research topic: $ARGUMENTS
Requires
parallel-cli≥ 0.3.0. If any command below errors withno such option,no such command, orunrecognized arguments, the user is on an older CLI. Tell them to runparallel-cli update(orpipx upgrade parallel-web-toolsif installed via pipx), then retry.
When to use (vs parallel-web-search)
ONLY use this skill when the user explicitly requests deep/exhaustive research. Deep research is 10-100x slower and more expensive than parallel-web-search. For normal "research X" requests, quick lookups, or fact-checking, use parallel-web-search instead.
Step 1: Start the research
Choose a descriptive filename based on the topic (e.g., ai-chip-market-2026, react-vs-vue-comparison). Use lowercase with hyphens, no spaces. Reuse this base name in step 2 as -o "$FILENAME".
parallel-cli research run "$ARGUMENTS" --processor pro-fast --text --no-wait --json
The --text flag tells the API to return a markdown report (with inline citations) when the task completes, instead of the default structured JSON. Use it for narrative/report-style requests, which is what most users want from "deep research." Drop --text if the user explicitly wants structured JSON output.
Optional with --text: pass --text-description "Keep under 1500 words, focus on M&A activity" to steer length, format, or focus.
If this is a follow-up to a previous research or enrichment task where you know the interaction_id, add context chaining:
parallel-cli research run "$ARGUMENTS" --processor lite-fast --text --no-wait --json --previous-interaction-id "$INTERACTION_ID"
By chaining interaction_id values across requests, each follow-up question automatically has the full context of prior turns — so you can drill deeper without restating what was already researched. Use a lighter processor (lite-fast or base-fast) for follow-ups since the heavy lifting was done in the initial turn.
This returns instantly. Do NOT omit --no-wait — without it the command blocks for minutes and will time out.
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 · 109 lines · 76 tokens per session scan A 9a797891bd98
parallel-deep-research is a skill published in the GitHub repository parallel-web/parallel-cursor-plugin (3 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 1,528 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 2026-08-31.
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…