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/change-grug/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/change-grug)<a href="https://agentmods.dev/skills/marin-community/marin/change-grug"><img src="https://agentmods.dev/badge/skills/marin-community/marin/change-grug/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/change-grug"><img src="https://agentmods.dev/badge/skills/marin-community/marin/change-grug.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 | $0.00020 | $0.00783 |
| Opus 5 | $0.00010 | $0.00392 |
| Sonnet 5 | $0.00004 | $0.00157 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
change-grug 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 12d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Changing Grug (Template-First)
Grug is intentionally template-first: the canonical edit surface lives in experiments/grug/base/, not in a shared levanter.grug trainer stack.
This skill covers two steps: trying a change in an experiment copy, and upstreaming it into the base template when it proves out.
Do not use this skill to run an existing variant, change launch-only configuration, or add a bounded operational diagnostic. Use the variant README and launcher controls for those tasks.
Source Of Truth
- Canonical template:
experiments/grug/base/—model.py,train.py,launch.py. - Variants:
experiments/grug/<variant>/— copy frombaseand modify locally (e.g. MoE). - One-off speedruns:
experiments/speedrun/...— useful for exploration, not canonical. - Reference branch for array-stacked grug variant wiring: https://github.com/marin-community/marin/tree/codex/array-stacked-grug-variant-pointer — useful for perf-focused experiments, especially improving compile times and reducing peak HBM.
Workflow
1) Pick one change bucket
Keep each pass scoped to one bucket:
- attention/masking
- block wiring/norm ordering
- MLP/activation
- loss kernel behavior
- optimizer/training loop behavior
2) Experiment in a copy
- Copy
experiments/grug/baseto a new variant directory. - Keep edits local and explicit (copy/paste over abstraction).
- Avoid introducing reusable framework surface unless there's clear repeated use.
3) Record the experiment
Update docs/reports/grug-archive.md with: path, origin (base, moe, or another source variant), commit SHA (when known), purpose, status (active, superseded, deleted), and diff link (prefer the CI-posted PR comment link; fallback to local report path).
For PRs that add a new experiments/grug/<variant>/, CI posts a visual diff comment automatically — copy that link into the archive entry.
For a local fallback, generate the diff report manually and link the report in the archive entry:
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.
- 12d ago First seen · 80 lines · 20 tokens per session scan A 38d24066dc1f
change-grug is a skill published in the GitHub repository marin-community/marin (3,593 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 783 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…