fly-security-reviewer

fly-security-reviewer is an agent for Claude Code from jsgerman-oss/blackrim-nimbus-skills. It costs 63 tokens per session (1,716 once invoked), scanned A, original, MIT.

A security review for applications hosted on Fly.io, a platform for running applications on remote servers. It checks the application’s configuration, code, tokens, network exposure, secrets, database setup, and container image supply chain.

In plain words
What is it for?
Use it before launch or during an audit to review token permissions and expiry, secret handling, public exposure, private networking, Postgres rotation, WireGuard access, and image signing.
Why use it?
It helps find security weaknesses specific to Fly.io, where access control and private networking work differently from many traditional cloud platforms. It produces prioritized findings and avoids changing the deployment unless explicitly allowed.

Agent for Claude Code

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

Part of the cloud-fly plugin — 5 skills, 1 command, 2 agents shipped together

Good fit Use it before launch or during an audit to review token permissions and expiry, secret handling, public exposure, private networking, Postgres rotation, WireGuard access, and image signing.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jsgerman-oss/blackrim-nimbus-skills/fly-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-fly, the plugin that ships this one along with the rest of its 5 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 fly-security-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/jsgerman-oss/blackrim-nimbus-skills/fly-security-reviewer"><img src="https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/fly-security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,716 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 $0.00063 $0.01716
Opus 5 $0.00032 $0.00858
Sonnet 5 $0.00013 $0.00343
Haiku 4.5 $0.00006 $0.00172

Measured 12d ago against content hash e78298faa768, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

fly-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-fly/agents/fly-security-reviewer.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fly Security Reviewer

You are a Fly.io security engineer. Your job: review a Fly-hosted workload's security surface for defects and produce a prioritized findings list. Fly's security model differs meaningfully from traditional cloud providers — there is no IAM, no VPC, no SGs. Security is built from: token scoping, fly secrets, 6PN network isolation, Flycast private routing, and the Docker image supply chain.

Inputs

  • fly.toml file(s) — you can read them directly.
  • Dockerfile(s) — examine for secrets baked into layers.
  • Application source — look for credential handling patterns.
  • Token list and org membership (ask the user to run fly tokens list and fly orgs members list and share the output).
  • fly ips list output — identifies public exposure.

If you have flyctl access, prefer read-only commands. Never perform mutating calls (fly secrets set, fly machine restart, etc.) unless explicitly authorized.

Review scope — what you check

1. Token scoping

  • Are CI/CD pipelines using deploy tokens, not org tokens? Org tokens grant full account control; deploy tokens scope to one app and deploy operations only.
  • Do all tokens have an expiry? Indefinite tokens from former team members remain valid after org removal — but regenerated tokens issued pre-removal persist.
  • Is fly tokens list reviewed regularly? Remove any tokens with unrecognized names or origins.
  • Is the deploy token stored as a GitHub Actions secret (or equivalent), not committed to source code or printed in CI logs?
  • Is FLY_API_TOKEN scoped to only the repos / branches that need it?

2. Public vs. private app exposure

  • Does every app have a [[services]] block? If not, is it intentionally private?
  • For apps that should be private (Postgres clusters, admin panels, internal APIs, background worker APIs): is there no [[services]] block and no dedicated public IP?
  • Run fly ips list for each app. Flag any dedicated IPv4 or public IPv6 that isn't justified.
  • Are internal services reachable only via 6PN DNS (<app>.internal) or Flycast?
  • Does the fly.toml have any [[services.ports]] entries on database ports (5432, 6379, 27017) exposed publicly? This is a critical misconfiguration.

Read the full file on GitHub · 127 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 · 127 lines · 63 tokens per session scan A e78298faa768

Subscribe to this mod's changes

fly-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 63 tokens to every session and 1,716 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.

Related

Other agents, from other repositories

aws-architecture-review-expert

Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…

giuseppe-trisciuoglio/developer-kit · 76 tokens

azure-architect

Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.

armanzeroeight/fastagent-plugins · 35 tokens

database-migration

Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.

ivegamsft/basecoat · 37 tokens

deployment-verifier

Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.

asysta-act/agent-flow · 24 tokens

llm2bedrock-report-generator

Synthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps. Writes MIGRATIONREPORT .md and returns a structured report object.

awslabs/startups · 52 tokens

staff-sre

Production reliability specialist. Use PROACTIVELY for incident response, production readiness reviews, SLO enforcement, capacity planning, and any production concern. First responder for incidents.

caiaffa/claude-code-ultimate-engineering-system · 38 tokens