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.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/instructions/marin-community/marin/agents-md)<a href="https://agentmods.dev/instructions/marin-community/marin/agents-md"><img src="https://agentmods.dev/badge/instructions/marin-community/marin/agents-md/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/instructions/marin-community/marin/agents-md"><img src="https://agentmods.dev/badge/instructions/marin-community/marin/agents-md.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 | $0.02889 | $0.02889 |
| Opus 5.5 | $0.01156 | $0.01156 |
| Sonnet 5.5 | $0.00578 | $0.00578 |
| Haiku 4.5 | $0.00289 | $0.00289 |
Grade A, and why
marin AGENTS.md 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 14d 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines for Marin
Start with the shared practices below. Consult subproject manuals for directory-specific guidance:
lib/levanter/AGENTS.md— Levanter (JAX training library)lib/marin/AGENTS.md— Marin (pipeline framework)lib/iris/AGENTS.md— Iris (job orchestration)lib/zephyr/AGENTS.md— Zephyr (dataset processing)lib/fray/AGENTS.md— Fray (distributed execution)
Operational Guides
For debugging and operating live infrastructure, read the relevant OPS.md:
lib/iris/OPS.md— cluster lifecycle, job/task management, profiling, SQL queries, GCP/CoreWeave operationslib/zephyr/OPS.md— pipeline debugging, straggler diagnosis, coordinator queries, diagnostic patterns.agents/ops/daytona.md— Daytona RL credentials, snapshot quota and stale-resource cleanup, sandbox lifecycle, and trial diagnostics
Zephyr OPS.md references Iris OPS.md for shared infrastructure commands — read Iris first when debugging zephyr jobs on Iris.
Infrastructure (Pulumi)
infra/ hosts several independent Pulumi projects following three distinct
patterns (infrastructure, application deploys, SaaS resource declarations). Read
infra/pulumi.md before creating or modifying a Pulumi project so new work
lands in the right pattern.
Workflow Playbooks
Skills are task-focused playbooks in .agents/skills/ (also accessible as
.claude/skills/). Before starting any non-trivial task, check whether a
matching skill exists by scanning the skill descriptions in your system
prompt. If a skill matches, invoke it via the Skill tool — do not skip it in
favor of ad-hoc commands.
Use the workflow catalog to choose the
skill that owns the requested outcome. Shared testing, writing, documentation,
and evidence policy lives in the linked guides. CI and scheduler procedures
live in infra/loom/procedures/ and apply only when assigned.
When adding, removing, or renaming skills, update the catalog and all callers.
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.
- 14d ago Changed · +14 lines · +238 tokens per session 9eea4742be3f
- 15d ago Changed · +12 lines · +164 tokens per session f5fe9ed46466
- 23d ago Changed · +1 lines · +28 tokens per session b337aadf03cc
- 25d ago Changed · +4 lines · +66 tokens per session b4a7b5fbe425
- 1mo ago Changed · -6 tokens per session d77cf1aa6866
- 1mo ago Changed · +2 lines · +20 tokens per session 4a41c103521b
- 1mo ago Changed · -31 lines · -500 tokens per session 54e1f2147aac
- 2mo ago Changed · +2 lines · +39 tokens per session 45b294cf14a5
- 2mo ago First seen · 248 lines · 2,840 tokens per session scan A f41441ef19b6
marin AGENTS.md is an instructions file published in the GitHub repository marin-community/marin (4,074 stars, last pushed today), licensed Apache-2.0. It adds 2,889 tokens to every session, about $0.0116 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 2026-08-30.
marin AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| marin AGENTS.mdmarin-community/marin | Instructions file | 4.1k | today | Apache-2.0 | A | 2,889 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |