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 lofcz/LLMTornado --skill deep-researchergit clone --depth 1 https://github.com/lofcz/LLMTornadoWrote 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/lofcz/llmtornado/deep-researcher)<a href="https://agentmods.dev/skills/lofcz/llmtornado/deep-researcher"><img src="https://agentmods.dev/badge/skills/lofcz/llmtornado/deep-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/skills/lofcz/llmtornado/deep-researcher"><img src="https://agentmods.dev/badge/skills/lofcz/llmtornado/deep-researcher.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 | $0.00027 | $0.01466 |
| Opus 5 | $0.00014 | $0.00733 |
| Sonnet 5 | $0.00005 | $0.00293 |
| Haiku 4.5 | $0.00003 | $0.00147 |
Grade A, and why
deep-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 11d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research Workflow
Copy this checklist and track your progress:
Deep Research Progress:
- [ ] Step 1: Define research scope and objectives
- [ ] Step 2: Conduct initial exploratory research
- [ ] Step 3: Deep dive into key areas
- [ ] Step 4: Cross-reference and validate findings
- [ ] Step 5: Synthesize and analyze information
- [ ] Step 6: Generate structured research report
Step 1: Define research scope and objectives
Clearly establish the research parameters:
- Main research question: What is the primary question or topic to investigate?
- Scope boundaries: What aspects should be included or excluded?
- Depth requirements: How detailed should the research be?
- Expected deliverables: What format and structure for the final output?
- Key areas of focus: What specific subtopics or angles to explore?
Document these parameters before proceeding to ensure focused and efficient research.
Step 2: Conduct initial exploratory research
Begin with broad reconnaissance to map the landscape:
- Search for overview information: Use search tools to find general information, definitions, and context
- Identify key sources: Look for authoritative sources, recent publications, and expert opinions
- Note initial findings: Create a preliminary list of important concepts, terms, and themes
- Discover related topics: Identify adjacent areas that may be relevant
- Assess information gaps: Note what information is readily available vs. what needs deeper investigation
Create an initial research map with main themes and subtopics identified.
Step 3: Deep dive into key areas
For each identified key area, conduct detailed investigation:
- Targeted searches: Use specific queries for each subtopic
- Multiple perspectives: Seek diverse viewpoints and approaches
- Technical details: Gather specific data, statistics, methodologies, or technical specifications
- Historical context: Understand the evolution and background
- Current state: Identify latest developments and trends
- Future outlook: Look for predictions, projections, or emerging patterns
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.
- 11d ago First seen · 165 lines · 27 tokens per session scan A 424c12c0de47
deep-researcher is a skill published in the GitHub repository lofcz/LLMTornado (639 stars, last pushed 24d ago), licensed MIT. It adds 27 tokens to every session and 1,466 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
author-pragma-dsl
Create and update validated pragma/v5 Expert, ExpertTeam, Flow, Evaluation, and Automation resources. Use when a user asks Pragma to create, change, configure, test, evaluate, or repair an Expert, team, Flow, Run Dry suite, schedule, trigger, or Automation in the current Pragma project.
portable-bundle-review
A review guide for portable Pragma bundles. A portable bundle is a packaged set of resources intended to work across environments.
pragma-code-review
A code-review guide written in Chinese. It reviews code across correctness, architectural boundaries, risk, and verification.
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
agent-orchestrator
Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…