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 simplicianokelly52/comet_mcp --skill comet-researchgit clone --depth 1 https://github.com/simplicianokelly52/comet_mcpWrote 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/simplicianokelly52/comet_mcp/comet-research)<a href="https://agentmods.dev/skills/simplicianokelly52/comet_mcp/comet-research"><img src="https://agentmods.dev/badge/skills/simplicianokelly52/comet_mcp/comet-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/simplicianokelly52/comet_mcp/comet-research"><img src="https://agentmods.dev/badge/skills/simplicianokelly52/comet_mcp/comet-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 | $0.00066 | $0.00760 |
| Opus 5 | $0.00033 | $0.00380 |
| Sonnet 5 | $0.00013 | $0.00152 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
comet-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 8d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comet Research Skill
Use the Comet MCP server to perform deep web research via Perplexity AI's agentic browser.
Available Tools
| Tool | Purpose |
|---|---|
comet_connect |
Connect to MCP-dedicated Comet browser (port 9223) |
comet_ask |
Send research query and get response |
comet_poll |
Check status of long-running research tasks |
comet_stop |
Stop current task if going off-track |
comet_mode |
Switch Perplexity mode (search/research/labs) |
comet_folders |
Manage research spaces (list/create/save) |
comet_library |
Search past research in Perplexity library |
comet_screenshot |
Capture current page state |
Quick Start
Simple Query (< 15 seconds)
comet_connect
comet_ask(prompt="What is [topic]?")
Deep Research (may take minutes)
comet_connect
comet_mode(mode="research")
comet_ask(prompt="Comprehensive analysis of [topic]", timeout=30000)
# If still processing, poll for completion
comet_poll()
Mode Selection Guide
Choose the appropriate mode based on the task:
| Mode | Use Case | Speed |
|---|---|---|
| search | Quick facts, definitions, simple questions | Fast (5-15s) |
| research | In-depth analysis, multiple sources, citations | Slow (30s-5min) |
| labs | Create files, apps, and visualizations | Medium |
Research Workflow
Step 1: Connect
Always start by connecting:
comet_connect
Step 2: Check/Set Mode
For complex research, switch to research mode:
comet_mode(mode="research")
Step 3: Send Query
comet_ask(
prompt="Your detailed research question here",
timeout=30000,
newChat=true
)
Step 4: Handle Long Tasks
If the response indicates the task is still running:
comet_poll()
Step 5: Save Important Research
comet_folders(action="save", name="My Research Space")
Best Practices
- Always connect first before any operation
- Use
newChat: truewhen switching to unrelated topics - Use research mode for comprehensive analysis
- Poll for long tasks instead of long timeouts
- Cite sources from the response in your answer
- Save valuable research to spaces for future reference
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.
- 8d ago First seen · 109 lines · 66 tokens per session scan A d6cef57dcd0a
comet-research is a skill published in the GitHub repository simplicianokelly52/comet_mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 66 tokens to every session and 760 once invoked, about $0.0003 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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…