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 brycewang-stanford/Auto-Empirical-Research-Skills --skill marimogit clone --depth 1 https://github.com/brycewang-stanford/Auto-Empirical-Research-SkillsWrote 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/brycewang-stanford/auto-empirical-research-skills/marimo)<a href="https://agentmods.dev/skills/brycewang-stanford/auto-empirical-research-skills/marimo"><img src="https://agentmods.dev/badge/skills/brycewang-stanford/auto-empirical-research-skills/marimo/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/brycewang-stanford/auto-empirical-research-skills/marimo"><img src="https://agentmods.dev/badge/skills/brycewang-stanford/auto-empirical-research-skills/marimo.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 | $0.00054 | $0.02749 |
| Opus 5 | $0.00027 | $0.01375 |
| Sonnet 5 | $0.00011 | $0.00550 |
| Haiku 4.5 | $0.00005 | $0.00275 |
Grade A, and why
marimo 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 5d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
8 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.
- 5d ago First seen · 290 lines · 54 tokens per session scan A a302f18ba70e
marimo is a skill published in the GitHub repository brycewang-stanford/Auto-Empirical-Research-Skills (3,759 stars, last pushed 5d ago), with no licence file. It adds 54 tokens to every session and 2,749 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 2026-09-07.
Other skills, from other repositories
planning-with-files
Use this by default for non-trivial multi-step work that needs persistent planning, progress tracking, or durable notes on disk. Trigger when a task will likely span multiple tool calls, research steps, verification loops, or enough context that the plan should not live only in transient chat memory.
calle
Use CALL-E from Codex through the calle CLI. Use for CALL-E setup checks, authentication recovery, phone call planning, planned call execution, and call status checks.
cost-aware-llm-pipeline
A planning guide for choosing language models and managing the amount of conversation context used by an AI coding workflow. It groups tasks by complexity and gives rules for avoiding context overflow during long sessions.
obsidian-kb-artifacts
Use this skill for Obsidian-native formatting and derived artifacts such as Markdown formatting, wikilinks, registry tables, canvas files, optional Bases, CLI operations, and link repair. This skill does not decide knowledge routing.
checkpoint-and-recover
Checkpoint state before risky operations, detect anomalies, and recover gracefully.
human-cli
Reach the actual human you're working for via the human CLI (ask/approve/choose/tell) when you need a decision, approval, or notification and no one is watching this terminal right now. Use for background/autonomous/scheduled runs, risky or irreversible actions, and genuine multi-way ambiguity — not for routine…