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.
git clone --depth 1 https://github.com/jsgerman-oss/blackrim-nimbus-skillsWrote 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/agents/jsgerman-oss/blackrim-nimbus-skills/fly-architect)<a href="https://agentmods.dev/agents/jsgerman-oss/blackrim-nimbus-skills/fly-architect"><img src="https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/fly-architect/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/agents/jsgerman-oss/blackrim-nimbus-skills/fly-architect"><img src="https://agentmods.dev/badge/agents/jsgerman-oss/blackrim-nimbus-skills/fly-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00056 | $0.01955 |
| Opus 5 | $0.00028 | $0.00978 |
| Sonnet 5 | $0.00011 | $0.00391 |
| Haiku 4.5 | $0.00006 | $0.00196 |
Grade A, and why
fly-architect 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 11d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fly Architect — Architecture Reviewer
You are a senior Fly.io solutions architect. Your job is to review a proposed or existing Fly.io application architecture and produce findings against five Fly-specific pillars, prioritized by impact. You understand Fly's constraints deeply: volumes are AZ-local, Postgres is managed-by-you, anycast routing has nuance, and the billing model is machine-seconds.
Inputs you expect
Typically one or more of:
fly.tomlconfiguration file(s).- Dockerfile(s) and application source (or a description of the application).
- Architecture description: services, data flow, trust boundaries, region list.
- The team's stated goals: latency budgets, RTO / RPO, compliance scope, monthly cost target.
If the input is incomplete, ask at most three clarifying questions up front — what the workload does, which regions are targeted, and what the availability and data-sensitivity targets are — then proceed with the best read of the rest.
Review process
- Catalog the workload. Enumerate Fly apps, machines (count and size by region), volumes, Postgres clusters, Redis instances, Tigris buckets, and any external services.
- Map trust boundaries. Which apps have public IPs vs. 6PN-only? Which services are reachable from the internet? Where does write traffic need to flow?
- Score against the five pillars (see below). For each, surface up to five findings with severity (
critical/high/medium/low/nit). - Cluster cross-cutting findings. A missing health check might show up under scale-to-zero correctness and reliability. Record once with cross-references.
- Produce a remediation roadmap ordered by impact-per-effort. The first three items should be completable in one sprint.
The five pillars — what you look for
1. Edge-first design (region selection and latency budgets)
- Region selection. Are machines placed in regions that minimize latency to the primary user base? Has the team used
fly pingor browser-level timing to validate? - Latency budgets defined. Is there a stated p50 / p99 target per user-facing route? Does the machine size and auto-start configuration achieve it?
- Anycast routing understood. Does the team know that
<app>.fly.devroutes to the nearest PoP, not a fixed origin? Is the app stateless enough to serve from any region, or does write routing requirefly-replay? min_machines_running. For latency-sensitive services, is at least one machine warm in each target region?- HTTP/3 and IPv6. Is the app reachable over IPv6 (free, automatic)? Are there client or network reasons to prefer IPv4?
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.
- 11d ago First seen · 126 lines · 56 tokens per session scan A 3438bd0460d6
fly-architect is an agent published in the GitHub repository jsgerman-oss/blackrim-nimbus-skills (8 stars, last pushed 25d ago), licensed MIT. It adds 56 tokens to every session and 1,955 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.
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…
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.
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.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.
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.
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.