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 skills add sofianbll/pplx-web-query --skill perplexity-webui-searchgit clone --depth 1 https://github.com/sofianbll/pplx-web-queryWrote 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/sofianbll/pplx-web-query/perplexity-webui-search)<a href="https://agentmods.dev/skills/sofianbll/pplx-web-query/perplexity-webui-search"><img src="https://agentmods.dev/badge/skills/sofianbll/pplx-web-query/perplexity-webui-search/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.
<a href="https://agentmods.dev/skills/sofianbll/pplx-web-query/perplexity-webui-search"><img src="https://agentmods.dev/badge/skills/sofianbll/pplx-web-query/perplexity-webui-search.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00055 | $0.00654 |
| Opus 5.5 | $0.00022 | $0.00262 |
| Sonnet 5.5 | $0.00011 | $0.00131 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
perplexity-webui-search 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perplexity WebUI Search
Overview
This skill runs the bundled Playwright script against Perplexity's web UI and returns the copied Markdown answer. It is a browser automation path, not an official Perplexity API client.
Use And Avoid
Use for explicit Perplexity tasks:
- Search Perplexity directly.
- Use Perplexity for research instead of generic webpage fetching.
- Retrieve or save a Perplexity answer through a visible browser session.
Do not use for:
- The user asks for a normal web fetch, URL extraction, or documentation lookup.
- The environment cannot open Chromium.
- Network access to
https://www.perplexity.ai/is unavailable. - The task requires an official Perplexity API.
Workflow
- Work from this skill directory, wherever it is installed.
- If dependencies are missing, run
npm install. - If Chromium is missing, run
npx playwright install chromium. - Run the search command with the user query and an output path.
- Read the output file before answering the user.
- If the browser is blocked, times out, copies an empty response, or the UI changes, say that clearly and do not claim Perplexity was searched.
Command
npm run search -- "<query>" ./result.md
The command opens visible Chromium, submits the query, waits for the final Copy button, writes the copied answer to the output file, and prints the answer to stdout. Progress logs go to stderr.
Output Handling
- Default output path:
result.md. - Prefer a task-specific path such as
./tmp/perplexity-result.mdwhen the user asks to preserve output. result.mdis generated output and should not be committed.- Read the output file and summarize the answer; do not just report that the command ran.
Response Pattern
- Success: summarize the Perplexity answer and include relevant citations copied in the output.
- Failure: state
Perplexity search did not complete: <concrete error>. Do not invent an answer or fall back to generic web search unless the user asks.
What ships with it
11 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.
- LICENSE 1.0 KB
- package-lock.json 1.8 KB
- package.json 827 B
- README.md 1.1 KB
- references/install-claude.md 775 B
- references/install-codex.md 1.1 KB
- references/install-opencode.md 1.6 KB
- references/troubleshooting.md 1.6 KB
- scripts/perplexity-core.js 4.2 KB runs code
- scripts/perplexity-core.test.mjs 3.1 KB runs code
- scripts/perplexity-query.js 435 B runs code
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.
- 1mo ago First seen · 70 lines · 55 tokens per session scan A 748fe27bee8b
perplexity-webui-search is a skill published in the GitHub repository sofianbll/pplx-web-query (5 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 654 once invoked, about $0.0002 per session on Opus 5.5. 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
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
babysit
Use when a user asks to babysit, monitor, keep checking, keep an eye on, or report when a pull request, CI run, ticket, deployment, or other changing target reaches an outcome.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
project-wiki
A system for creating and maintaining a project wiki: a set of organized documents that explain a software project's plans, rules, references, and progress.
mindos-zh
A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…