What is review-grant?

A review procedure for an identified marin-iac grant pull request that changes identity-and-access data or a deployment-target module. IAM controls who can access cloud resources.

Use it to inspect the pull request, verify that only approved grant files changed, decrypt principals, get confirmation, and apply the confirmed grant.

It ensures the encrypted identities and roles are revealed and confirmed by a person before access is applied.

How marin-community/marin configures Claude Code and Codex

About the project

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.

marin-community/marin · 4,074 stars · on GitHub · marin.community

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/marin-community/marin/main/.agents/skills/review-grant/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/marin-community/marin

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/marin-community/marin/review-grant/github.svg)](https://agentmods.dev/skills/marin-community/marin/review-grant)

Your own site

<a href="https://agentmods.dev/skills/marin-community/marin/review-grant"><img src="https://agentmods.dev/badge/skills/marin-community/marin/review-grant/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/marin-community/marin/review-grant"><img src="https://agentmods.dev/badge/skills/marin-community/marin/review-grant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,087 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00037	$0.01087
Opus 5.5	$0.00015	$0.00435
Sonnet 5.5	$0.00007	$0.00217
Haiku 4.5	$0.00004	$0.00109

Measured 2mo ago against content hash 88a5bb7e5d1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-grant 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 2mo 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.

.agents/skills/review-grant/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Review a user grant

A grant PR (usually from the add-grant skill) uses opaque human-NNN references whose emails are KMS ciphertext in iam_data.yaml. This skill reveals the real grant, gets an explicit human confirmation, then lands it and applies it.

Read first:

infra/pulumi/README.md — the marin-iac stacks and the pulumi up prerequisites (you need roles/cloudkms.cryptoKeyEncrypterDecrypter on the key and permission to update the marin stack).

Never approve or merge before the user confirms the decrypted grant. The whole point is that a second person sees the actual identity and access before it is applied.

1. Fetch the PR

gh pr view <n> --repo marin-community/marin --json title,body,headRefName,files,url
gh pr checkout <n>          # pull the branch into the worktree
git fetch origin main

Confirm the diff only touches grant surfaces under infra/pulumi/src/iac/gcp/: iam_data.yaml and/or a deploy-target IAM module. If it changes anything else (code, other Pulumi resources), stop and review it as an ordinary PR, not a grant.

2. Decrypt the changed principals

Turn the changed opaque principal references into real emails:

git diff origin/main...HEAD -- infra/pulumi/src/iac/gcp \
  | uv run --package marin-iac --extra deploy \
      python infra/pulumi/iam_principal.py decrypt --diff

Each output line is + user:<email> (added) or - user:<email> (removed). Map each back to the role and resource it sits under in the diff. The decryptor shows the principal; read the surrounding role and container (project_grants, a specific bucket/secret/repository/service account, or a deploy-target module) from the diff hunk.

3. Present the grant and get confirmation

Print a plain-language summary, one line per grant, and ask the user to confirm. For example:

PR #1234 grants:
  + [email protected] → roles/storage.objectViewer on project hai-gcp-models
  + [email protected] → IAP viewer on evaldash.oa.dev
  - [email protected] → roles/bigquery.dataViewer (revoked)
Apply this? (yes/no)

Read the full file on GitHub · 118 lines

Changes

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.

2mo ago First seen · 118 lines · 37 tokens per session scan A 88a5bb7e5d1b

Subscribe to this mod's changes

review-grant is a skill published in the GitHub repository marin-community/marin (4,074 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 1,087 once invoked, about $0.0001 per session on Opus 5.5. 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.

Cloud DevOps and cloud Security

review-grant next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
review-grantmarin-community/marin	Skill	4.1k	today	Apache-2.0	A	37	Claude Code, Codex
gke-compute-classesgoogle/skills	Skill	22k	yesterday	Apache-2.0	A	83	Claude Code, Codex
gke-reliabilitygoogle/skills	Skill	22k	yesterday	Apache-2.0	A	85	Claude Code, Codex
gke-workload-securitygoogle/skills	Skill	22k	yesterday	Apache-2.0	A	171	Claude Code, Codex
cloud-architectJeffallan/claude-skills	Skill	12k	7d ago	MIT	A	71	Claude Code
nemo-automodel-launcher-configNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	30	Claude Code
azure-mgmt-botservice-dotnetmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	78	Claude Code

marin: Skill for Claude Code