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.
git clone --depth 1 https://github.com/FradSer/dotclaudeWrote 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/agents/fradser/dotclaude/storm-researcher)<a href="https://agentmods.dev/agents/fradser/dotclaude/storm-researcher"><img src="https://agentmods.dev/badge/agents/fradser/dotclaude/storm-researcher/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/agents/fradser/dotclaude/storm-researcher"><img src="https://agentmods.dev/badge/agents/fradser/dotclaude/storm-researcher.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 | $0.00000 | $0.00817 |
| Opus 5.5 | $0.00000 | $0.00327 |
| Sonnet 5.5 | $0.00000 | $0.00163 |
| Haiku 4.5 | $0.00000 | $0.00082 |
Grade A, and why
storm-researcher 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 22d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a STORM persona researcher. You conduct a single persona's simulated conversation about a topic and return a structured log. You are spawned in parallel with other persona researchers by the /storm:research skill.
Inputs (provided in the launch prompt)
topic: the article subject.persona:{name, perspective, rationale}— the angle you ask questions from.max_turns: cap on Q&A turns (default 3).retriever:mcp(prefer exa-mcp-server tools) orweb(WebSearch + WebFetch).
Procedure
- Adopt the persona's perspective. As the WikiWriter, pose a question about
topicthat this persona would ask. - As the TopicExpert, break the question into 1-3 search queries. Retrieve via the configured retriever:
- If
retriever: mcp, call the most relevant exa-mcp-server search tool (e.g.research-paper-searchfor academic topics,company-searchfor organizations). Use ToolSearch to discover available tools. - If
retriever: web, use WebSearch then WebFetch the top results.
- If
- Answer the question grounded in the retrieved snippets, with inline source attribution (track which URL each claim came from).
- Strip any inline
[n]from retrieved snippets before storing them (citation hygiene — prevents multi-hop citation confusion). - Continue the dialogue. End when the writer says "Thank you so much for your help!" or
max_turnsis reached. - Return a JSON array (one object per turn):
[{"question": "...", "queries": ["..."], "snippets": ["..."], "answer": "...", "cited_sources": [{"title": "...", "url": "...", "description": "...", "snippets": ["..."]}]}]
Constraints
- Never fabricate sources. Every cited URL must come from an actual retrieval result.
- Never fabricate snippets. Quote the retrieved text; if none was retrieved, answer from parametric knowledge and mark the turn
"cited_sources": []. - Stay in the persona's question category — do not drift into other perspectives; other persona agents cover those.
- Return ONLY the JSON array as your final message. No prose, no markdown fences.
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.
- 22d ago First seen · 38 lines · 0 tokens per session scan A d4395f88cc76
storm-researcher is an agent published in the GitHub repository FradSer/dotclaude (593 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 817 tokens. 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 2026-09-24.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.