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 tomzx/agents --skill research-topicgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/research-topic)<a href="https://agentmods.dev/skills/tomzx/agents/research-topic"><img src="https://agentmods.dev/badge/skills/tomzx/agents/research-topic/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/tomzx/agents/research-topic"><img src="https://agentmods.dev/badge/skills/tomzx/agents/research-topic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 279 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00124 | $0.03566 |
| Opus 5 | $0.00062 | $0.01783 |
| Sonnet 5 | $0.00025 | $0.00713 |
| Haiku 4.5 | $0.00012 | $0.00357 |
Grade A, and why
research-topic scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. Optionally downloads images: with `--with-images`, it mirrors the page with `wget -p -k` so images are saved and `<img src>` is rewritten to local relative paths, then trafilatura emits markdown whose image links poin How it starts
The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Topic
Given any topic, runs a comprehensive web search across multiple angles and source types, snapshots every page it visits (raw HTML plus a clean markdown conversion), and synthesizes a structured research document. The snapshots stay on disk so every claim in the final document can be traced back to the exact content that was read, and the material can be re-used later without re-fetching.
Prerequisites
- Topic: The subject to investigate (e.g., "how WebRTC handles NAT traversal", "React Server Components vs. Remix", "the 2024 SQLite virtual table changes")
- Scope (optional but recommended): The specific question or angle, time bounds (e.g., "last 2 years"), and how many sources to deep-read (default 8-12)
- Seed sources (optional): Any URLs the user already knows matter
- Output directory (optional): Defaults to
./research/<topic-slug>/relative to the current working directory
Tools
This skill does its fetching, image handling, and conversion through one script: scripts/snapshot.py (next to this file).
The script owns every deterministic decision so the skill steps stay focused on research judgment, not tool mechanics.
Run it with uv run; the # /// script preamble declares its Python dependencies (trafilatura, structlog), so uv installs them into an ephemeral environment on first use, no project setup required.
uv run <skill_dir>/scripts/snapshot.py --help
Resolve <skill_dir> to this skill's directory (the directory containing this SKILL.md).
What the script does
For each URL it:
- Fetches the exact served bytes with a browser User-Agent and writes them to
raw.html(the canonical archive). - Converts to clean markdown through a cascade, recording which converter won in
meta.json:- trafilatura (preferred), a content extractor: it strips navigation, sidebars, footers, and boilerplate, then emits the article as markdown, and captures title, author, and date. It is a Python package (adbar/trafilatura, Apache-2.0), benchmark-validated and used by HuggingFace, IBM, and Microsoft Research. In an empirical comparison on chrome-heavy pages (Wikipedia, GitHub), trafilatura produced 3-13x smaller markdown with near-zero nav/footer noise, versus the pure converters below.
- html2markdown (first fallback), a pure converter (JohannesKaufmann/html-to-markdown) that keeps nav/footer but respects local image links.
- pandoc (last resort), a pure converter, present on most systems.
- Optionally downloads images: with
--with-images, it mirrors the page withwget -p -kso images are saved and<img src>is rewritten to local relative paths, then trafilatura emits markdown whose image links point at those local files. Images wget cannot fetch stay as remote URLs.
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.
- 6d ago First seen · 314 lines · 124 tokens per session scan A dbc311ad62b7
research-topic is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 124 tokens to every session and 3,566 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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…