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/lint-review/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/lint-review)<a href="https://agentmods.dev/skills/marin-community/marin/lint-review"><img src="https://agentmods.dev/badge/skills/marin-community/marin/lint-review/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/lint-review"><img src="https://agentmods.dev/badge/skills/marin-community/marin/lint-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 30 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 | $0.00036 | $0.01323 |
| Opus 5 | $0.00018 | $0.00661 |
| Sonnet 5 | $0.00007 | $0.00265 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
lint-review 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 13d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Lint-catalog review on a PR
Run the infra/lint/ catalog review (./infra/pre-commit.py --review)
over a pull request's branch diff and surface every finding — as file:line
inline review comments where the finding's line is available, and as a
single fallback comment for the rest.
Your contract
You are running the review and reporting its output. You are read-only except
for posting comments: never edit, stage, commit, push, or "fix" anything, and
never run a state-changing git/gh command. The review's own lane agents are
already locked read-only.
Report the findings faithfully. The --review run (its lanes + composer) is
the authority on what is a finding: post each surviving finding verbatim —
one comment per finding. Do not drop, merge, reword the substance of, soften,
re-judge, or invent findings. Silently losing a real finding is the one
unforgivable error; so is fabricating one.
Steps
-
Idempotency guard (only with
--comment). Check whether this skill has already posted on the PR: look for the marker<!-- marin-lint-review -->in both issue comments (gh pr view <PR> --json comments) and inline review comments (gh api repos/{owner}/{repo}/pulls/<PR>/comments --paginate). If the marker is present, stop now — the PR already has a lint pass and we do not want duplicate comments. Otherwise continue. -
Run the review. From the repo root:
head_sha="$(git rev-parse HEAD)" MARIN_REVIEW_TRIGGER=ci \ MARIN_REVIEW_PR_NUMBER=<PR> \ MARIN_REVIEW_HEAD_SHA="$head_sha" \ ./infra/pre-commit.py --review --agent-command='codex exec'The command writes its raw per-arm prompts/outputs and the combined findings under
/tmp/marin-linter/<branch>/<timestamp>-<uniq>/(path printed at the end); read it if a run looks wrong. -
Collect the findings. Each finding the command emits on stdout is one line in the canonical catalog format:
<path>:<line>: ml-<code> (<confidence>) <message>
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.
- 13d ago First seen · 121 lines · 36 tokens per session scan A 19b8f82bfb7f
lint-review is a skill published in the GitHub repository marin-community/marin (3,607 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 1,323 once invoked, about $0.0002 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.
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.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…