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/skills/review-pr/SKILL.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/skills/marin-community/marin/review-pr)<a href="https://agentmods.dev/skills/marin-community/marin/review-pr"><img src="https://agentmods.dev/badge/skills/marin-community/marin/review-pr/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/skills/marin-community/marin/review-pr"><img src="https://agentmods.dev/badge/skills/marin-community/marin/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Prompt Injection · line 46 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 103 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00020 | $0.01135 |
| Opus 5 | $0.00010 | $0.00567 |
| Sonnet 5 | $0.00004 | $0.00227 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
review-pr 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review a pull request
Review the requested pull request at the exact head named by the caller. The
review is read-only except for comments posted when --comment is requested.
Review standard
A reviewable Marin pull request:
- Implements the behavior claimed by its title and description without an introduced correctness, security, state-transition, or error-handling defect.
- Follows the root and path-scoped
AGENTS.mdorCLAUDE.mdinstructions. If tests change, it also follows rootTESTING.mdand any scoped testing guide. - Keeps public interfaces, invariants, dependency direction, configuration, and types coherent across every changed call site. Marin does not preserve backward compatibility unless the request explicitly requires it.
- Uses tests for behavior rather than implementation details, incidental prose, private state, tautologies, or mocks below an I/O boundary.
- Keeps abstraction proportional to demonstrated reuse. Flag a maintainability problem only when the change creates a concrete structural obstacle, hidden assumption, or distant coupling that materially constrains nearby work.
- Keeps documentation synchronized with behavior. The pull-request title and
body must follow
.agents/skills/writing-style/pull-requests.md; the body is the squash-merge commit message, not a template, file inventory, or test log.
Report only actionable defects introduced by the pull request. Validate every
finding against the diff, relevant surrounding code, and applicable
instructions. Do not report style preferences, speculative failures, harmless
duplication in experiments/grug, or pre-existing problems. If the evidence is
uncertain, omit the finding.
Workflow
- Inspect the pull request metadata, issue comments, inline comments, and current head. Stop without commenting when the pull request is closed, a draft, an automated dependency update, or too trivial to benefit from code review. Still review agent-generated pull requests.
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 Changed · -80 lines · +2 tokens per session a5331d3b6ef2
- 10d ago First seen · 195 lines · 18 tokens per session scan A 5678134b0e83
review-pr is a skill published in the GitHub repository marin-community/marin (3,548 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 1,135 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.