marin: Skill for Claude Code

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

run-ferries is a skill for Claude Code, Codex from marin-community/marin. It costs 22 tokens per session (2,086 once invoked), scanned A, original, Apache-2.0.

A procedure for launching, monitoring, or sealing Marin canary and daily ferry runs. These are controlled machine-learning training checks used to test a configuration or integration.

In plain words
What is it for?
Use it for explicitly requested canary health checks or daily experiments involving the specified data, model, hardware, logs, and run references.
Why use it?
It adds required preparation and approval steps before a training run is launched, then records and monitors the run.

Skill for Claude CodeCodex

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

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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/ferries/daily_analysis.py \.

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-ferries/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-ferries

README.md
[![agentmods](https://agentmods.dev/badge/skills/marin-community/marin/run-ferries/github.svg)](https://agentmods.dev/skills/marin-community/marin/run-ferries)
Your own site
<a href="https://agentmods.dev/skills/marin-community/marin/run-ferries"><img src="https://agentmods.dev/badge/skills/marin-community/marin/run-ferries/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-ferries

Your own site · 80×15
<a href="https://agentmods.dev/skills/marin-community/marin/run-ferries"><img src="https://agentmods.dev/badge/skills/marin-community/marin/run-ferries.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,086 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 warn 7 Sept 2026
SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 32
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 90
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Agent Snooping · line 141
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 168
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00022 $0.02086
Opus 5 $0.00011 $0.01043
Sonnet 5 $0.00004 $0.00417
Haiku 4.5 $0.00002 $0.00209

Measured 9d ago against content hash 5cf728eff87e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

run-ferries 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-ferries/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ferries

  • experiments/ferries/canary_ferry.py (MoE canary, TPU and GPU via CANARY_ACCELERATOR)
  • experiments/ferries/daily.py

Canary is the stable, low-cost health check. Daily exercises a larger envelope with one or two explicit changes.

Shared baseline:

  • data: shared nemotron_mix baseline
  • default cluster: us-central1 (zone us-central1-a)
  • run log: docs/experiments/daily-ferry-log.md

Daily defaults to llama_150m, sequence length 4096, batch size 512, and about 1e19 FLOPs unless its configuration says otherwise.

Inputs Before Proposing (Daily Only)

Canary runs normally do not require a proposal cycle or PR. For daily, collect:

  1. Last ferry references: issue URL, PR/commit URL, W&B run URL and Iris job ID
  2. Human objective for this interval: standard integration pass, or explicit regression investigation
  3. Interval boundary: use "since last ferry run", not fixed wall-clock day boundaries

If objective is ambiguous, ask before editing.

Operating Policy

General

  • Hard launch gate: get explicit requester approval before launching any ferry job. Only exception: the requester explicitly says to launch without asking.
  • Follow the use-iris skill's job-monitoring workflow until the run reaches a terminal state (SUCCEEDED/FAILED/STOPPED); do not stop early. Full ferry monitoring often takes 4-5 hours.
  • Never restart/recreate/mutate cluster without explicit human consent in-thread. Keep cluster mutation guardrails aligned with the Iris monitoring workflow, including the debug exception path.
  • Use major-event updates (not spam): launch, first eval, major incident, terminal state.
  • Seal each completed daily run with a pushed git tag pointing to the exact launch commit.
  • Canonical run-closure PR labels: ferry, ferry-daily, ferry-log-only, ferry-sealed.
  • Canonical seal-tag format (daily): ferry/daily/YYYYMMDD/<run_slug>

Canary

  • Keep canary stable; only change it for explicit reliability fixes, and only when diagnosing/fixing a concrete failure mode.
  • Canary launches usually do not require a PR if the script/config is unchanged.
  • If canary fails, treat as urgent infrastructure/training-health triage.
  • Canary is run-only by default (W&B + issue updates); no sealing tag or run-closure PR in the normal path.

Read the full file on GitHub · 184 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 · 184 lines · 22 tokens per session scan A 5cf728eff87e

Subscribe to this mod's changes

run-ferries is a skill published in the GitHub repository marin-community/marin (3,512 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 2,086 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