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/background-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/background-research)<a href="https://agentmods.dev/skills/marin-community/marin/background-research"><img src="https://agentmods.dev/badge/skills/marin-community/marin/background-research.svg" alt="Measured on agentmods" 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 | $0.01123 |
| Opus 5 | $0.00014 | $0.00562 |
| Sonnet 5 | $0.00005 | $0.00225 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
background-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 8d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Background research
Effort
State the effort level at the top of the output. Stop when new sources no longer change the ranked hypotheses; go longer only when the user asks or the decision is expensive enough to justify it.
low(3-7 min): current issue/logbook, obvious local refs, and a few external sources. Use for small follow-ups or when the user provides strong context.medium(10-15 min): default. Search internal Marin sources plus targeted external literature/code, include a contradiction pass, and produce a source ledger plus ranked next experiments.high(30-60 min): for expensive runs, architecture changes, data/eval decisions, or public claims. Use subagents for independent tracks when useful: internal Marin corpus, external literature/code, and W&B/report sources. Record query strings and rejected-source notes.
Effort changes breadth and provenance depth, not claim quality. Even low
effort must cite sources and distinguish evidence from speculation.
Search Order
Search internal and external sources in parallel when useful, but do not skip the internal pass. Prefer durable artifacts over transient conversation.
- Current issue, PR, research logbook, or design file.
- GitHub issues and PRs, especially experiment issues and linked comments.
docs/reports/index.md,docs/reports/,docs/experiments/, model cards.- Existing logbook files and
.agents/projects/*/research.md. - Relevant code and experiment definitions under
experiments/,lib/, and long-lived research branches or tags. - W&B reports/runs and Data Browser links surfaced from issues, reports, or logbooks.
- External papers, blog posts, official docs, codebases, arXiv, OpenReview, Semantic Scholar, and cited references.
For external search, include at least one adversarial query family for
medium/high.
Design-Doc Mode
When write-design-doc uses this skill, the output usually lands in
.agents/projects/<slug>/research.md. Keep it focused on design inputs, not
experiment execution.
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.
- 8d ago First seen · 129 lines · 27 tokens per session scan A 5b6d508bdf06
background-research is a skill published in the GitHub repository marin-community/marin (3,476 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 1,123 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…