marin: Skill for Claude Code

.agents/skills/run-research/SKILL.md

run-research is a skill for Claude Code, Codex from marin-community/marin. It costs 24 tokens per session (1,072 once invoked), scanned A, original, Apache-2.0.

A workflow for running a research project across multiple sessions while keeping a lasting record of decisions, evidence, hypotheses, code, and results.

In plain words
What is it for?
Use it for explicitly requested, long-running investigations that need a logbook, research branch, saved configurations, reproducible experiments, snapshots, and possibly a production branch for review and merging.
Why use it?
It prevents long research from becoming a collection of disconnected conversations or losing the steps needed to reproduce important findings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is marin-community/marin's own configuration. It tells Claude Code and Codex how to work on marin itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything marin configures →

About the project

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.

marin-community/marin · 3,512 stars · on GitHub · marin.community

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/marin-community/marin/main/.agents/skills/run-research/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/marin-community/marin

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for run-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/marin-community/marin/run-research/github.svg)](https://agentmods.dev/skills/marin-community/marin/run-research)
Your own site
<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.

agentmods 80×15 button for run-research

Your own site · 80×15
<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>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,072 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 0d788d6b5d06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

.agents/skills/run-research/SKILL.md · 106 lines

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

  1. A logbook at .agents/logbooks/<topic>.md.
  2. A living hypothesis queue in the logbook, derived from append-only entries and updated as hypotheses are proposed, blocked, falsified, or promoted.
  3. A long-lived branch, for example research/<topic> or research/<user>/<issue>-<topic>, with the logbook, research code, configs, small artifacts, and test harnesses needed to reproduce results.
  4. One or more commit or tag snapshots for meaningful milestones.
  5. Often a "production" branch that gets PR'd and merged.

Standard Workflow

1. Prologue

  1. Keep an existing user-specified branch; otherwise create or use a long-lived research/<topic> or research/<user>/<issue>-<topic> branch.
  2. If a coordinating issue exists, link it bidirectionally with the logbook.
  3. Choose one short experiment ID prefix and use IDs such as MOE-HC-001 in entries, runs, and comments; use two to four shared tags.
  4. Record the goal, success and stop criteria, baseline, initial hypothesis queue and experiment matrix, relevant code, and references.

2. Research Loop

  1. Forage: gather prior work and local context.
  2. Propose: update the living hypothesis queue and pick the next test.
  3. Run: implement the smallest useful experiment and collect evidence.
  4. Interpret: compare against baseline, decide confidence, and update the logbook.
  5. Promote: move decision-relevant claims into the current summary and a coordinating issue when one exists.
  6. Seal: snapshot durable results or extract production work.

Read the full file on GitHub · 106 lines

Changes

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.

  1. 9d ago First seen · 106 lines · 24 tokens per session scan A 0d788d6b5d06

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens