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 xpepper/perplexity-agent-skill --skill perplexity-web-researchgit clone --depth 1 https://github.com/xpepper/perplexity-agent-skillWrote 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/xpepper/perplexity-agent-skill/perplexity-web-research)<a href="https://agentmods.dev/skills/xpepper/perplexity-agent-skill/perplexity-web-research"><img src="https://agentmods.dev/badge/skills/xpepper/perplexity-agent-skill/perplexity-web-research/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/xpepper/perplexity-agent-skill/perplexity-web-research"><img src="https://agentmods.dev/badge/skills/xpepper/perplexity-agent-skill/perplexity-web-research.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 | $0.00073 | $0.01479 |
| Opus 5.5 | $0.00029 | $0.00592 |
| Sonnet 5.5 | $0.00015 | $0.00296 |
| Haiku 4.5 | $0.00007 | $0.00148 |
Grade A, and why
perplexity-web-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 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perplexity Web Research
Use the llm CLI with Perplexity plugin for web research, deep reasoning, and independent validation.
Quick Start
llm -m sonar 'your question here'
Model Selection
| Model | Use Case | Context | Web Search |
|---|---|---|---|
sonar |
Quick lookups, general questions (default) | 128k | ✓ |
sonar-pro |
Thorough answers, detailed research | 200k | ✓ |
sonar-deep-research |
Complex multi-faceted research | 128k | ✓ |
sonar-reasoning |
Step-by-step reasoning questions | 128k | ✓ |
sonar-reasoning-pro |
Advanced reasoning with detail | 128k | ✓ |
r1-1776 |
Reasoning without web search | 128k | ✗ |
Start with sonar for most queries. Upgrade to other models when you need comprehensive coverage (sonar-pro), complex synthesis (sonar-deep-research), or logical reasoning (sonar-reasoning/sonar-reasoning-pro).
For detailed selection criteria, decision flowcharts, and examples, see references/model-selection-guide.md.
When to Use
Use this skill in three primary scenarios:
1. Current or External Knowledge
When you need up-to-date information and intentionally want to use Perplexity instead of standard web fetch tools:
- Documentation lookups: Current API docs, library references, framework guides
- Library versions: "What's the latest version of X?"
- Recent changes: "What changed in Y version 2.0?"
- Error research: Unfamiliar error messages or stack traces
- Technology verification: "Does X support Y feature?"
- Current events: Recent news, announcements, releases
- Fact checking: Information that may have changed since training cutoff
2. Second Opinions
When you want an independent perspective before committing to a decision or approach:
- Architecture decisions: "What are the trade-offs between approach A and B?"
- Technology choices: "Should I use X or Y for this use case?"
- Design validation: "Is this approach considered best practice?"
- Problem verification: "Am I thinking about this problem correctly?"
- Alternative perspectives: "What other ways could this be solved?"
What ships with it
4 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.
- 1mo ago First seen · 172 lines · 73 tokens per session scan A f1dcede3411e
perplexity-web-research is a skill published in the GitHub repository xpepper/perplexity-agent-skill (19 stars, last pushed 8mo ago), licensed MIT. It adds 73 tokens to every session and 1,479 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
clean-architecture-dotnet
Use when domain logic leaks into API/Infrastructure, project references violate layer boundaries, or you need to decide between CQS (always), CQRS bus (complex domains), and DDD patterns (invariants and events).
outside-in-tdd
Use when writing tests from the outside-in, defining behavior before code, or any feature where tests should start from observable business behavior and let internal design emerge.
setup-husky-dotnet
Use when configuring Git hooks in .NET projects before team commits occur, to enforce commit message standards and code formatting automatically.
finding-files
Use when searching for files by name, pattern, or type in large directories, or building file lists for pipelines with other tools.
querying-json
Use when querying JSON files, filtering or transforming JSON data, or extracting specific fields from large JSON files without loading entire file contents (saves 80-95% context).
searching-text
Use when searching for text patterns across files, finding specific code locations, or getting lines with surrounding context in a single call.