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/x-cmd/skill/denarionpx skills add x-cmd/skill --skill denariogit clone --depth 1 https://github.com/x-cmd/skillWrote 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/x-cmd/skill/denario)<a href="https://agentmods.dev/skills/x-cmd/skill/denario"><img src="https://agentmods.dev/badge/skills/x-cmd/skill/denario.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 | $0.00069 | $0.01373 |
| Opus 5 | $0.00034 | $0.00687 |
| Sonnet 5 | $0.00014 | $0.00275 |
| Haiku 4.5 | $0.00007 | $0.00137 |
Grade A, and why
denario 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 yesterday.
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.
This is a copy
88% identical to denario — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Denario
Overview
Denario is a multiagent AI system designed to automate scientific research workflows from initial data analysis through publication-ready manuscripts. Built on AG2 and LangGraph frameworks, it orchestrates multiple specialized agents to handle hypothesis generation, methodology development, computational analysis, and paper writing.
When to Use This Skill
Use this skill when:
- Analyzing datasets to generate novel research hypotheses
- Developing structured research methodologies
- Executing computational experiments and generating visualizations
- Conducting literature searches for research context
- Writing journal-formatted LaTeX papers from research results
- Automating the complete research pipeline from data to publication
Installation
Install denario using uv (recommended):
uv init
uv add "denario[app]"
Or using pip:
uv pip install "denario[app]"
For Docker deployment or building from source, see references/installation.md.
LLM API Configuration
Denario requires API keys from supported LLM providers. Supported providers include:
- Google Vertex AI
- OpenAI
- Other LLM services compatible with AG2/LangGraph
Store API keys securely using environment variables or .env files. For detailed configuration instructions including Vertex AI setup, see references/llm_configuration.md.
Core Research Workflow
Denario follows a structured four-stage research pipeline:
1. Data Description
Define the research context by specifying available data and tools:
from denario import Denario
den = Denario(project_dir="./my_research")
den.set_data_description("""
Available datasets: time-series data on X and Y
Tools: pandas, sklearn, matplotlib
Research domain: [specify domain]
""")
2. Idea Generation
Generate research hypotheses from the data description:
den.get_idea()
This produces a research question or hypothesis based on the described data. Alternatively, provide a custom idea:
What ships with it
4 files 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.
- yesterday First seen · 215 lines · 69 tokens per session scan A bd9e8e3b25e6
denario is a skill published in the GitHub repository x-cmd/skill (26 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,373 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to denario, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
kaggle-research-compute
Use when a research or engineering task needs automatic heavy-compute routing to free Kaggle Kernels through the local broker, with agent-driven push, poll, fetch, and a multi-run resume loop across concurrent kernels; free CPU (quota-free) and GPU under a self-imposed weekly GPU-hour cap.
lean-strict-verification-gate
Use when checking whether a Lean artifact can safely support a research claim.
modal-research-compute
Use when a research or engineering task needs automatic heavy-compute routing through the unified local broker, including Modal-backed remote CPU, high-memory CPU, or GPU execution.
digest-bridge
Use when the user wants to extract arXiv IDs or DOIs from research or RSS digests and turn them into getscipapers requests or manifests.
lean-research-library
Use when any Lean formalization task starts (reuse Mathlib and the personal research library before proving anything new) and when it ends (gate finished results into the library and flag mathlib-PR candidates, always asking the user first). Also scaffolds and publishes paper artifacts from the personal template.
venue-ranking-evidence
Use when identifying a journal, conference, or proceedings series from a partial name, acronym, alias, ISSN, or source ID; preserving source-specific rank, quartile, metric, classification, membership, or coverage observations; or proving that the public ICORE detail page displayed one ICORE claim. Live bulk paths are…