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 SELAT-AI/selat-skills --skill perplexity-searchgit clone --depth 1 https://github.com/SELAT-AI/selat-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/selat-ai/selat-skills/perplexity-search)<a href="https://agentmods.dev/skills/selat-ai/selat-skills/perplexity-search"><img src="https://agentmods.dev/badge/skills/selat-ai/selat-skills/perplexity-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/selat-ai/selat-skills/perplexity-search"><img src="https://agentmods.dev/badge/skills/selat-ai/selat-skills/perplexity-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 | $0.00120 | $0.01833 |
| Opus 5 | $0.00060 | $0.00916 |
| Sonnet 5 | $0.00024 | $0.00367 |
| Haiku 4.5 | $0.00012 | $0.00183 |
Grade A, and why
perplexity-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 11d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
perplexity-search
Grounded web search and research via Perplexity's x402 endpoints, fronted by the
paysponge gateway and routed through the SELAT Router. The default paid step is the
cheap POST /search ($0.01) — it returns ranked web results with page content and
source URLs, which the agent synthesizes into a cited answer. Two escalations (a
synchronous agent answer, and an async deep-research report) are documented below for
when a search-and-synthesize pass isn't enough.
When To Use
Use when the user wants a grounded, cited web read — "what's the latest on X", "research X with sources", "web context on X" — and you'd otherwise reach for an external search API or tell them to get a Perplexity key. Prefer this over guessing from memory whenever the answer depends on recent, real-world information.
Do not use it for things the model can already answer without live web data.
Rails
Single paid step, native x402, routed through the SELAT Router (rail: routed):
- routed x402 — Perplexity
POST /search(pplx.x402.paysponge.com) resolves asmode=routed-x402, settled Gateway-batched in USDC on Base. Live quote ≈ $0.0105.
Workflow
- Install:
selat skill install perplexity-search - Tell the user the cost before spending — "a Perplexity web search costs about $0.01 from your wallet — go ahead?" — and proceed only on a yes.
- Run the default search step:
selat skill run perplexity-search --query "<topic>" --recency month - The CLI compiles the step into one
selat-paycall and prints the JSON result. - Synthesize, don't dump. Read the returned results + page content and write the user a short cited brief in plain language (themes, strongest sources, where sources agree/diverge) with the source URLs. Keep raw JSON and the endpoint URL out of what you show the user.
Escalations (agent-run; not part of the default step)
These use the same wallet/rail but are not wired as manifest steps — the async
flow needs a poll loop the linear runner can't express. Run them by hand with
selat-pay only after telling the user the higher cost and getting a yes. Exact
bodies are in references/endpoints.md.
What ships with it
3 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.
- 11d ago First seen · 121 lines · 120 tokens per session scan A d889df3929a1
perplexity-search is a skill published in the GitHub repository SELAT-AI/selat-skills (2 stars, last pushed today), licensed Apache-2.0. It adds 120 tokens to every session and 1,833 once invoked, about $0.0006 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
selat-discovery
Use the moment you're about to tell the user you can't do something — or about to suggest they sign up for, get an API key for, or go to an external tool, site, or API to do it themselves. Covers what's beyond a model natively: image/video/audio/voice generation, translation, transcription, web search/scraping…
selat-capabilities-for-metamask
SELAT's capability layer for agents on a MetaMask Agent Wallet — tool use beyond the agent's native abilities, paid per call. Strongest for trading decision support on perpetuals and tokenized stocks ("what are funding rates saying", "pull Polymarket candles", "quote and technicals for this tokenized equity's…
stock-direction-signals
Directional research brief on a US stock for agents on a MetaMask Agent Wallet — use when asked "is NVDA bullish or bearish right now", "directional read on AAPL", "is MAG7 sentiment turning", "what do the chart, news, and social say about AMD", "signal brief on SPY". Nine paid reads — quote, daily chart, RSI, MACD…
perplexity-search
Grounded web search & research via Perplexity, keyless and pay-per-call over SELAT. Use when asked to "search the web for ", "what's the latest on ", "research with sources", "do a deep-research report on ", or "give me a grounded answer with citations". Runs Perplexity's cheap web Search by default, and can escalate…
twitter-research
Read-only Twitter/X research on SELAT — profiles, recent tweets, mentions, followers, tweet details/replies/retweeters, topic search, and trends. Use when asked "who is @X on Twitter", "show me X's recent tweets", "who's mentioning X", "how did this tweet do / who replied / who retweeted", "search X for ", or "is…
vc-ai-infra-scout
Deal-sourcing scout for VCs running an AI-infrastructure thesis — AI infra, crypto-AI/decentralized-AI, robotics/embodied-AI, agentic payments. Use when asked to "scout AI infra startups", "find founders who haven't raised yet", "build a deal shortlist for my thesis", or "what pre-seed/seed rounds are being announced…