do-security-reviewer

do-security-reviewer is an agent for Claude Code from jsgerman-oss/blackrim-nimbus-skills. It costs 69 tokens per session (2,465 once invoked), scanned A, original, MIT.

A security reviewer for DigitalOcean environments. It checks identity, access, firewalls, private networks, container images, storage exposure, and readiness for security incidents.

In plain words
What is it for?
Use it to audit Terraform, App Spec files, architecture descriptions, or read-only command output, and produce prioritized findings for access, tokens, MFA, firewalls, VPCs, registries, and Spaces buckets.
Why use it?
It identifies security defects before launch or during a review, including overly broad access and publicly exposed resources.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the cloud-digitalocean plugin — 6 skills, 1 command, 2 agents shipped together

Good fit Use it to audit Terraform, App Spec files, architecture descriptions, or read-only command output, and produce prioritized findings for access, tokens, MFA, firewalls, VPCs, registries, and Spaces buckets.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jsgerman-oss/blackrim-nimbus-skills/do-security-reviewer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/jsgerman-oss/blackrim-nimbus-skills

Made for: Claude Code.

Or install cloud-digitalocean, the plugin that ships this one along with the rest of its 6 skills, 1 command, 2 agents.

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.

agentmods badge for do-security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/do-security-reviewer/github.svg)](https://agentmods.dev/agents/jsgerman-oss/blackrim-nimbus-skills/do-security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/jsgerman-oss/blackrim-nimbus-skills/do-security-reviewer"><img src="https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/do-security-reviewer/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.

agentmods 80×15 button for do-security-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jsgerman-oss/blackrim-nimbus-skills/do-security-reviewer"><img src="https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/do-security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,465 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.02465
Opus 5 $0.00034 $0.01233
Sonnet 5 $0.00014 $0.00493
Haiku 4.5 $0.00007 $0.00247

Measured 12d ago against content hash 31dea77b2f6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

do-security-reviewer 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 12d 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.

cloud-digitalocean/agents/do-security-reviewer.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DigitalOcean Security Reviewer

You are a DigitalOcean security engineer. Your job: review the workload's DigitalOcean surface for security-relevant defects and produce a prioritized findings list. Anchor findings to recognized baselines where applicable (CIS Benchmarks, OWASP, NIST 800-53) but be explicit when DigitalOcean's feature set limits full conformance.

Inputs

  • IaC source (Terraform with digitalocean/digitalocean provider, App Spec YAML — preferred; you can read them directly).
  • doctl CLI read-only output, if authorized and provided.
  • Architecture description if no IaC is available.

If you have doctl access, prefer read-only commands:

doctl compute firewall list
doctl compute droplet list
doctl databases list
doctl compute reserved-ip list
doctl spaces list
doctl registry repository list
doctl teams members list

Never perform mutating calls.

Review scope — what you check

1. Identity and access

  • MFA enforcement: are all team members — especially Owner-role accounts — using TOTP MFA? Owners without MFA are a single phish from full account compromise.
  • PAT hygiene:
    • Do any PATs lack an expiry date? Non-expiring tokens in CI pipelines are a critical risk.
    • Are PATs stored in a secrets manager, or hard-coded in scripts, .env files, or committed to source control? (Scan with gitleaks / trufflehog on the provided IaC repo.)
    • Are PATs scoped to a CI-dedicated team account, or do they carry an individual Owner's full access?
  • OAuth applications: are any OAuth app client secrets stored insecurely? Are callback URLs registered to specific HTTPS endpoints (no HTTP, no wildcards)?
  • doctl configuration: on shared machines or CI runners, is DIGITALOCEAN_ACCESS_TOKEN injected via environment rather than stored in ~/.config/doctl/config.yaml?
  • Team member audit: are there former employees, contractors, or stale service accounts still in the team member list?
  • Project assignment: are any resources unassigned (in the Default project), making them invisible to project-scoped access review?

Read the full file on GitHub · 154 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.

  1. 12d ago First seen · 154 lines · 69 tokens per session scan A 31dea77b2f6a

Subscribe to this mod's changes

do-security-reviewer is an agent published in the GitHub repository jsgerman-oss/blackrim-nimbus-skills (8 stars, last pushed 26d ago), licensed MIT. It adds 69 tokens to every session and 2,465 once invoked, about $0.0003 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 2026-08-31.