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.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/marin-community/marin/task-snapshotnpx skills add marin-community/marin --skill task-snapshotgit 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/task-snapshot)<a href="https://agentmods.dev/skills/marin-community/marin/task-snapshot"><img src="https://agentmods.dev/badge/skills/marin-community/marin/task-snapshot.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00304 |
| Opus 5 | $0.00015 | $0.00152 |
| Sonnet 5 | $0.00006 | $0.00061 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
task-snapshot 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 5d 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: Task Snapshot
Use this when a result, milestone, or handoff needs stable references that will remain valid as a branch keeps moving.
Snapshot Choices
- Use a commit link for ordinary task milestones.
- Use an annotated tag for meaningful experiment checkpoints, published numbers, or long-lived handoffs.
- Include only relevant files in the snapshot commit.
Snapshot Comment
When posting a snapshot to an issue or PR, include:
- Commit or tag link.
- Pinned GitHub tree/file links for logbooks, benchmark outputs, configs, and reports.
- Exact command(s).
- Relevant details like: hardware/cluster and device count; critical, durable, non-secret environment variables; primary comparison table or a link to W&B/report artifacts.
Pinned GitHub tree links should include the commit or tag, for example:
https://github.com/marin-community/marin/tree/<commit-or-tag>/.agents/logbooks/<topic>.md
Prefer to use anchor text, even if it's just the filename.
Validation
Before presenting a snapshot as evidence:
- The command is reproducible from the snapshot.
- Shapes/configs and environment are explicit.
- The logbook and issue link to the same result.
- Dense data has an artifact, W&B, or dashboard link.
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.
- 5d ago First seen · 44 lines · 29 tokens per session scan A 8a6df5984de1
task-snapshot is a skill published in the GitHub repository marin-community/marin (3,403 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 304 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
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
crew-commit
Canonical commit workflow for Gas Town crew members: pre-flight checks, branch creation, gt commit with agent identity, push, and PR creation. Use when ready to commit and submit work for review.
cherry-pick
Cherry-pick a commit from main to a Sui release branch, create the release PR, and report the PR URL.
mflux-pr
Make a clean PR in mflux (inspect diff, quick verification, commit, push, open PR) using repo conventions.
comet-safe-delivery
在保护无关脏改动、关联 worktree、子模块和用户明确边界的前提下，提交、推送、合并或完成范围明确的 Comet 变更。用户要求提交、推送、合并回目标分支、清理 worktree 或交付已准备好的改动时使用。.
changelog
Auto-generates a changelog from git commits, sprint data, and design documents. Produces both internal and player-facing versions.