Marin is an open-source research program, software platform, and community for developing foundation models such as large language models. Researchers use it for data preparation, tokenization, pretraining, posttraining, evaluation, and related experiments, including work on audio-text, DNA, and protein models. The catalogue entries are add-ons that support workflows around Marin.
Borrowing it
Nothing to install: this file belongs to marin-community/marin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marin-community/marin/main/.agents/skills/run-research/SKILL.mdgit clone --depth 1 https://github.com/marin-community/marinWrote 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/marin-community/marin/run-research)<a href="https://agentmods.dev/skills/marin-community/marin/run-research"><img src="https://agentmods.dev/badge/skills/marin-community/marin/run-research/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/marin-community/marin/run-research"><img src="https://agentmods.dev/badge/skills/marin-community/marin/run-research.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 | $0.00024 | $0.01072 |
| Opus 5 | $0.00012 | $0.00536 |
| Sonnet 5 | $0.00005 | $0.00214 |
| Haiku 4.5 | $0.00002 | $0.00107 |
Grade A, and why
run-research 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 9d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-session research
Long-lived work should leave a durable record: a logbook and enough commands/config to reproduce results. When the work has a coordinating issue, keep its summary current. Do not publish secrets or private work the user asks to hold back.
Use background-research, task-logbook, wandb-reporting, task-snapshot,
and update-docs for their named artifacts. Add a domain skill only when the
research directly requires its workflow.
Core Artifacts
- A logbook at
.agents/logbooks/<topic>.md. - A living hypothesis queue in the logbook, derived from append-only entries and updated as hypotheses are proposed, blocked, falsified, or promoted.
- A long-lived branch, for example
research/<topic>orresearch/<user>/<issue>-<topic>, with the logbook, research code, configs, small artifacts, and test harnesses needed to reproduce results. - One or more commit or tag snapshots for meaningful milestones.
- Often a "production" branch that gets PR'd and merged.
Standard Workflow
1. Prologue
- Keep an existing user-specified branch; otherwise create or use a long-lived
research/<topic>orresearch/<user>/<issue>-<topic>branch. - If a coordinating issue exists, link it bidirectionally with the logbook.
- Choose one short experiment ID prefix and use IDs such as
MOE-HC-001in entries, runs, and comments; use two to four shared tags. - Record the goal, success and stop criteria, baseline, initial hypothesis queue and experiment matrix, relevant code, and references.
2. Research Loop
- Forage: gather prior work and local context.
- Propose: update the living hypothesis queue and pick the next test.
- Run: implement the smallest useful experiment and collect evidence.
- Interpret: compare against baseline, decide confidence, and update the logbook.
- Promote: move decision-relevant claims into the current summary and a coordinating issue when one exists.
- Seal: snapshot durable results or extract production work.
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.
- 9d ago First seen · 106 lines · 24 tokens per session scan A 0d788d6b5d06
run-research is a skill published in the GitHub repository marin-community/marin (3,512 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 1,072 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
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…