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/write-testsnpx skills add marin-community/marin --skill write-testsgit 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/write-tests)<a href="https://agentmods.dev/skills/marin-community/marin/write-tests"><img src="https://agentmods.dev/badge/skills/marin-community/marin/write-tests.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 | $0.00024 | $0.00363 |
| Opus 5 | $0.00012 | $0.00181 |
| Sonnet 5 | $0.00005 | $0.00073 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
write-tests 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
Write Tests
Read these before choosing test style, fixtures, mocks, markers, or commands:
- root
AGENTS.md - root
TESTING.md - the nearest subproject
AGENTS.mdfor files underlib/* - package testing docs referenced from that
AGENTS.md, such aslib/iris/TESTING.md
Workflow
- Find existing tests for the touched behavior before creating a new file.
- Check module-specific testing rules for commands, markers, fakes, mocks, and numerical tolerances.
- Name the behavior that should fail if the code is wrong.
- Write the smallest test that observes that behavior through a public API, structured output, persisted state, or real side effect.
- For a bug, write the regression test before the fix and confirm it fails.
- Keep test setup realistic but small. Use fixtures and parameterization to remove duplication.
- Run the narrow test first, then the relevant package test command. Before a
PR, run the repo lint entry point required by
AGENTS.md.
Default Commands
- Run a narrow test path while editing, then run
uv run --no-project infra/ci/run_tests.py. Do not override the repository's default marker expression. - For package-specific commands, use the relevant
lib/*/AGENTS.mdor testing doc.
Before a PR, run ./infra/pre-commit.py --changed-files --fix or --all-files
as appropriate. Do not substitute uv run pre-commit.
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 · 40 lines · 24 tokens per session scan A fbe7a18f976f
write-tests is a skill published in the GitHub repository marin-community/marin (3,354 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 363 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…