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/jakkaj/tools/perplexity-deep-researchnpx skills add jakkaj/tools --skill perplexity-deep-researchgit clone --depth 1 https://github.com/jakkaj/toolsWrote 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/jakkaj/tools/perplexity-deep-research)<a href="https://agentmods.dev/skills/jakkaj/tools/perplexity-deep-research"><img src="https://agentmods.dev/badge/skills/jakkaj/tools/perplexity-deep-research.svg" alt="Measured on agentmods" 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 | $0.00124 | $0.00877 |
| Opus 5 | $0.00062 | $0.00439 |
| Sonnet 5 | $0.00025 | $0.00175 |
| Haiku 4.5 | $0.00012 | $0.00088 |
Grade A, and why
perplexity-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 5d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
perplexity-deep-research
A tiny bundled CLI (pplx_research.py, Python stdlib only) that POSTs straight to
Perplexity's HTTP API with a long client-side timeout, so deep research jobs finish
instead of dying at the MCP's ~5-minute cap.
When to use this vs the perplexity MCP
| Situation | Use |
|---|---|
| Quick fact, summary, single question (seconds) | perplexity MCP (perplexity_ask) — simplest |
| Deep / multi-source research, expected > 5 min | this skill (sonar-deep-research) |
| MCP call timed out | this skill |
Prerequisites
PERPLEXITY_API_KEYin the environment (already present in this setup's env and every MCP config). The CLI reads it directly; no extra config.python3(stdlib only — nothing to install).
Usage
The CLI (pplx_research.py) lives next to this file in the skill folder. Invoke it
with python3, pointing at the installed path (skills install to
~/.agents/skills/perplexity-deep-research/, symlinked into ~/.claude/skills/):
# Deep research (default model = sonar-deep-research, default timeout = 1800s/30min)
python3 ~/.agents/skills/perplexity-deep-research/pplx_research.py "Survey the current state of X, with sources"
# Or cd into the skill folder first, then call it directly
cd ~/.agents/skills/perplexity-deep-research && python3 pplx_research.py "your deep research question here"
# Quick / cheap call with the fast model
python3 pplx_research.py --model sonar "what is the capital of France?"
# Give it even longer, and bias toward recent sources
python3 pplx_research.py --timeout 2400 --recency month "what changed recently in Y?"
# Raw JSON (for programmatic use)
python3 pplx_research.py --json "..."
Options
| Flag | Default | Meaning |
|---|---|---|
prompt (positional) |
— | The research question |
--model |
sonar-deep-research |
sonar, sonar-pro, or sonar-deep-research |
--timeout |
1800 |
Client timeout (seconds). This is the knob that beats the MCP's ~5-min cap. |
--system |
— | Optional system prompt |
--recency |
— | hour / day / week / month / year |
--json |
off | Print raw API response instead of formatted text |
What ships with it
1 file 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.
- 5d ago First seen · 77 lines · 124 tokens per session scan A 9d61434dc7c1
perplexity-deep-research is a skill published in the GitHub repository jakkaj/tools (5 stars, last pushed 19d ago), licensed MIT. It adds 124 tokens to every session and 877 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…