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/wandb-reporting/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/wandb-reporting)<a href="https://agentmods.dev/skills/marin-community/marin/wandb-reporting"><img src="https://agentmods.dev/badge/skills/marin-community/marin/wandb-reporting/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/wandb-reporting"><img src="https://agentmods.dev/badge/skills/marin-community/marin/wandb-reporting.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 | $0.00029 | $0.00390 |
| Opus 5 | $0.00015 | $0.00195 |
| Sonnet 5 | $0.00006 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
wandb-reporting 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 10d 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.
What it actually says
Skill: W&B Reporting
Use W&B when scalar series, plots, large comparison tables, or raw artifacts are too dense for issue comments or logbooks. Keep GitHub as the narrative layer and W&B as the data/report layer.
Project Policy
- Choose project scope by the type signature of the work.
- Default to the
marinproject for pretraining runs. - Use a new project for materially different work, such as kernel development or a new RL variant.
- Runs requiring explicit run-to-run comparison must share a W&B project.
- Decide scope early; you cannot reliably move or copy runs across projects later.
Run Naming and Metadata
- Use the same experiment/task ID in W&B run names, logbook entries, and issue comments.
- Group related sweeps with a stable group name.
- Prefer artifacts for raw CSV/JSON outputs that feed published tables.
Reporting
- Link W&B runs/reports from the coordinating issue and logbook.
- Summarize only the decision-relevant numbers in GitHub; link W&B for dense tables and plots.
- Before publishing a claim, verify expected row counts, key uniqueness, and any de-duplication or aggregation logic.
- Keep report titles and sections aligned with the issue/logbook labels.
- Keep artifacts small (<10MB). Larger artifacts should be stored in the experiment dir and linked.
Completion Checklist
- Relevant runs are in the intended project.
- Run names map back to issue/logbook experiment IDs.
- Primary comparison table or chart is linked from the issue.
- Raw artifacts needed to reproduce the table are uploaded or linked.
- Claims in GitHub match the final W&B values.
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.
- 10d ago First seen · 46 lines · 29 tokens per session scan A 5c32d8497e44
wandb-reporting is a skill published in the GitHub repository marin-community/marin (3,548 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 390 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…