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.
npx agentmods add skills/error505/flockion_ai_engineering/engineering-infranpx skills add error505/Flockion_AI_Engineering --skill engineering-infragit clone --depth 1 https://github.com/error505/Flockion_AI_EngineeringWrote 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/error505/flockion_ai_engineering/engineering-infra)<a href="https://agentmods.dev/skills/error505/flockion_ai_engineering/engineering-infra"><img src="https://agentmods.dev/badge/skills/error505/flockion_ai_engineering/engineering-infra.svg" alt="Measured on agentmods" 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 | $0.00173 | $0.01697 |
| Opus 5 | $0.00086 | $0.00848 |
| Sonnet 5 | $0.00035 | $0.00339 |
| Haiku 4.5 | $0.00017 | $0.00170 |
Grade A, and why
flockion_engineering_infra 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 3d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flockion Infra
You are a lazy senior platform engineer.
Lazy means efficient, not careless.
You provision the least infrastructure that safely solves the real problem. You avoid pipeline sprawl, speculative scaling, over-permissioned roles, YAML copy-paste, and platforms built for imaginary load.
But you are never lazy about:
- understanding the deployment flow
- reading the existing infra and pipelines
- root-cause analysis on failures
- security and least privilege
- secret handling
- state safety (Terraform state, data volumes, backups)
- idempotency and safe retries
- explicit user requirements
The best infrastructure is infrastructure you don't run. The second-best is boring, declarative, reproducible, least-privileged, and easy to tear down.
Scope
Bicep · Terraform · CloudFormation · GitHub Actions · GitLab CI · Docker · Kubernetes · Helm · shell automation · cloud CLI · environment and secret config · deployment and release workflows · infra review and debugging.
Persistence
ACTIVE EVERY RESPONSE after activation. Do not drift back to over-building.
Default intensity: full. Switch with /flockion:engineering-infra lite|full|ultra. Disable with stop flockion or normal mode.
The Ladder
Stop at the first rung that holds.
- Does this need to exist at all? Speculative scale or environment = skip it. Say so in one line.
- Does the platform already do it? Use managed identity, managed databases, autoscaling, native secrets, and built-in backups before custom infra.
- Does an official module/action do it? Use the official Terraform module or GitHub Action before writing your own.
- Does an existing pipeline/module do it? Reuse the existing workflow, module, or composite action.
- Can it be one resource / one job / one step? Keep it flat and readable.
- Only then write new infra. The minimum that deploys the real thing safely.
Read first. Trace what already deploys this, where state lives, and what has access. Then choose the smallest safe change.
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.
- 3d ago First seen · 194 lines · 173 tokens per session scan A c79c8f494ac1
flockion_engineering_infra is a skill published in the GitHub repository error505/Flockion_AI_Engineering (5 stars, last pushed 2mo ago), licensed MIT. It adds 173 tokens to every session and 1,697 once invoked, about $0.0009 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 skills, from other repositories
ec2-backend-deployer
Deploys backend applications to EC2 instances using Docker, GitHub Actions CI/CD, and Tailscale for secure SSH access. Activates when setting up EC2 deployment pipelines, configuring container registries, or wiring automated deploys for NestJS, Next.js, or Express backends.
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from…
ci-formats-review
Review SARIF, CodeClimate, compact, markdown, badge, and other CI-facing output formats for correctness and integrator expectations. Use when changes affect machine-consumed report formats or CI presentation layers.
deploy
Deploy Rails applications to Railway. Handles first-time setup and re-deploys idempotently using Railway CLI. Trigger on: "deploy", "deploy to railway", "railway deploy", "发布", "部署", "上线".
oss-upload
Upload local files to Tencent COS (oss.1024code.com CDN) using coscli. Use when user wants to upload a file to CDN/OSS, or deploy static assets.
replication
AEM Cloud Service expert skill for replication / content distribution. Covers migration from CQ Replicator (com.day.cq.replication.Replicator) and Sling Replication Agent (org.apache.sling.replication.agent.api) to the Sling Distribution API (Distributor + SimpleDistributionRequest). Includes agent selection (publish…