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-ops-lognpx skills add marin-community/marin --skill write-ops-loggit 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-ops-log)<a href="https://agentmods.dev/skills/marin-community/marin/write-ops-log"><img src="https://agentmods.dev/badge/skills/marin-community/marin/write-ops-log.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 | $0.00027 | $0.00742 |
| Opus 5 | $0.00014 | $0.00371 |
| Sonnet 5 | $0.00005 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
write-ops-log 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Write an Ops Log
Publish the incident record to Echo. Do not add a repository debug-log file. The audience is a future engineer who must quickly decide what to check or do next. Record the smallest set of facts that supports that action. Link raw evidence and detailed chronology rather than reproducing them; Echo entries consume limited model context whenever they are retrieved.
Search before writing
Invoke consult-echo and run its complete search-before-write sequence. Edit
the existing entry when it covers the same incident. Start with a natural-language
infra/echo/cli.py search, fetch likely matches with get <source-id>, and use
grep for the exact error or run identifier. Create a new entry for a different
incident even when the symptom resembles an older one; link related incidents
and create or extend a separate synthesis only when they establish a reusable
cross-incident pattern.
Draft the Echo entry
Write an OKF document in a temporary file:
---
type: wiki-note
title: "Incident YYYY-MM-DD: <system> — <symptom>"
use_when: when investigating <specific symptom or exact error>
tags:
- incident
- debugging
- ops
- <system>
- <severity>
- <resolution>
---
# <System or component>: <symptom>
## TL;DR
- <user-visible symptom>
- <diagnostic discriminator or immediate action>
- <fix or remaining caveat>
## Response
<The shortest safe procedure for diagnosing, mitigating, or avoiding the
incident.>
## Cause and resolution
<Only the evidence needed to justify the response and explain the resolution.>
## Artifacts
- <Canonical PR, issue, dashboard, durable log bundle, or report>
Use the incident's investigation date. Use lowercase kebab-case tags and no
more than 20. Always include incident and debugging; add ops for
infrastructure work, followed by the subsystem, severity, and resolution.
Omit any body section that adds no actionable value. Add a compact original
report, investigation step, or course correction only when it changes how a
future reader should recognize or respond to the incident.
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 · 102 lines · 27 tokens per session scan A 9268cd898edd
write-ops-log is a skill published in the GitHub repository marin-community/marin (3,354 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 742 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.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…