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/marina-app/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/marina-app)<a href="https://agentmods.dev/skills/marin-community/marin/marina-app"><img src="https://agentmods.dev/badge/skills/marin-community/marin/marina-app/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/marina-app"><img src="https://agentmods.dev/badge/skills/marin-community/marin/marina-app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00043 | $0.01723 |
| Opus 5.5 | $0.00017 | $0.00689 |
| Sonnet 5.5 | $0.00009 | $0.00345 |
| Haiku 4.5 | $0.00004 | $0.00172 |
Grade A, and why
marina-app 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 7d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work with Marina applications
Read Building Marina apps and the relevant sections of the Marina reference. Treat source, CLI help and those docs as authoritative. Use the existing examples as package references.
Every application uses marina release. Choose where to keep source based on
expected future changes:
- If the app will need changes again, check its source into
infra/marina/apps/<name>/for review and maintenance. - Ad hoc means no future changes are expected. Release it from any local directory without checking in its source, as with a finished report.
Both store released packages in Postgres; ad hoc apps remain available after
release. Agent-created apps follow the same rules. Named-app capabilities are
a separate decision from where source lives.
Use marina apps for management. The existing package format still uses
applet.toml and applet_id; these do not define a separate app type.
Marina image deployment and startup never publish packages, select application
revisions, or run application migrations.
Do not restart Marina to release an application.
Source and package
Use applet.toml, dist/index.html, optional browser assets, and optional Python
modules. A declared build_command can generate dist/. Maintained sources declare
the stable applet_id and optional shared build inputs in source_paths within
the same applet.toml, as the named apps do for infra/marina/web. Keep existing UUIDs,
names, database schemas and data locations when updating an application.
Prefer plain HTML/JavaScript for small reports and Vue/Vite for substantial client
state. UUID apps need relative asset/API URLs, Vite base: "./", and hash routing.
Named applications may retain their existing route bases. Bundle dependencies;
executable inline scripts and third-party script CDNs are blocked.
An optional python_entrypoint = "server.app:create_api" names a factory returning
an ASGI app. Root modules and backend/ modules also work. Return
registered_api(api) to expose annotated FastAPI operations through MCP. Use relative
intra-application imports and installed shared libraries. Dependencies must already
exist in Marina's base environment.
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.
- 7d ago First seen · 173 lines · 43 tokens per session scan A 992ddacfe976
marina-app is a skill published in the GitHub repository marin-community/marin (4,074 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 1,723 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-30.
marina-app compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| marina-appmarin-community/marin | Skill | 4.1k | today | Apache-2.0 | A | 43 | Claude Code, Codex |
| stripe-projectsNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 15 | Claude Code, Codex |
| alchemy-providerpingdotgg/t3code | Skill | 48k | today | MIT | A | 153 | Claude Code, Codex |
| django-storages-s3Jeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 138 | Claude Code |
| websocket-engineerJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 36 | Claude Code |
| azure-eventhub-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 94 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |