Borrowing it
Nothing to install: this file belongs to escapeWu/perplexity-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/escapeWu/perplexity-ai/main/.agents/skills/perplexity-search/SKILL.mdgit clone --depth 1 https://github.com/escapeWu/perplexity-aiWrote 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/escapewu/perplexity-ai/perplexity-search)<a href="https://agentmods.dev/skills/escapewu/perplexity-ai/perplexity-search"><img src="https://agentmods.dev/badge/skills/escapewu/perplexity-ai/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/escapewu/perplexity-ai/perplexity-search"><img src="https://agentmods.dev/badge/skills/escapewu/perplexity-ai/perplexity-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00084 | $0.01710 |
| Opus 5.5 | $0.00034 | $0.00684 |
| Sonnet 5.5 | $0.00017 | $0.00342 |
| Haiku 4.5 | $0.00008 | $0.00171 |
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 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perplexity Search
Use one workflow regardless of transport. A connected perplexity-mcp server exposes tools directly; the bundled scripts/client.py exposes matching Python methods over REST.
| Operation | MCP tool | Python REST method |
|---|---|---|
| Focused search or cited answer | perplexity_ask_v2 |
client.perplexity_ask_v2(...) |
| Broad Deep Research | perplexity_research_v2 |
client.perplexity_research_v2(...) |
| Submit detached work | perplexity_task_submit |
client.perplexity_task_submit(...) |
| Observe detached work | perplexity_task_status |
client.perplexity_task_status(...) |
| Cancel detached work | perplexity_task_cancel |
client.perplexity_task_cancel(...) |
Choose the available transport, then keep the same operation names, arguments, session rules, and output handling. Do not switch to legacy MCP tools such as search, research, or perplexity_search; they are deprecated.
Python REST client
The client uses only the Python standard library. Load it from this skill's scripts directory:
import sys
from pathlib import Path
skill_dir = Path(".agents/skills/perplexity-search").resolve()
sys.path.insert(0, str(skill_dir / "scripts"))
from client import PerplexityRestClient
client = PerplexityRestClient.from_config(skill_dir / "config.json")
result = client.perplexity_ask_v2(
"What changed in Python packaging this month? Cite primary sources."
)
Configuration is shared by every REST method:
PPLX_BASE_URL: service root, with or without/v1; defaults tohttp://127.0.0.1:8000.MCP_TOKENorPPLX_API_KEY: bearer token;MCP_TOKENtakes precedence.config.json: fallback configuration when environment variables are absent.
Never print, quote, log, or commit real credentials.
Focused Ask
Use perplexity_ask_v2 for current facts, news, comparisons, source-backed analysis, and ordinary searches.
MCP arguments and Python arguments are identical:
{
"query": "Compare the latest Python packaging changes and cite primary sources.",
"model": "gpt-5-6-terra",
"thinking": true,
"session_id": null,
"files": null
}
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 Changed · +59 lines · -14 tokens per session fc3b904954c4
- 1mo ago First seen · 141 lines · 98 tokens per session scan A 1f6e85f5a775
perplexity-search is a skill published in the GitHub repository escapeWu/perplexity-ai (177 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,710 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
reverse-skill
A collection of methods for analyzing websites, browser code, API behavior, and encryption or signing processes. It is intended for authorized investigation and produces findings and reports rather than launching attacks.
sub2api-admin
Manage Sub2API admin APIs for accounts, redeem codes, groups, proxies, error passthrough rules, TLS fingerprint profiles, imports, exports, batch updates, and raw administrator API calls. Use when the user mentions Sub2API, admin API keys, account management, redeem code management, recharge codes, invitation codes…
reverse-engineering
Provides reverse engineering techniques. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, malware-like loaders, and anti-debug or anti-analysis logic. Do not use it…
dsl-vm-reverse
Reverse JavaScript-based custom DSL/VM interpreters, non-standard WASM-like runtimes, and risk-control engines. Use when analyzing IIFE or switch-based opcode dispatchers, extracting instruction tables, recovering bytecode semantics, capturing VM state at runtime, or reconstructing execution flow.
docs-generator
Creates task-oriented technical documentation with progressive disclosure. Use when writing READMEs, API docs, architecture docs, or markdown documentation. Also use this skill at the END of any completed reverse engineering, penetration testing, CTF, or security analysis task to generate a formal report in the user's…
js-reverse
A workflow for investigating how browser JavaScript finds data, creates signed or encrypted values, and sends requests. It uses browser observation, runtime sampling, and captured evidence to explain the code's behavior.