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 skills add WingedGuardian/GENesis-AGI --skill aws-fde-deliverygit clone --depth 1 https://github.com/WingedGuardian/GENesis-AGIWrote 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/wingedguardian/genesis-agi/aws-fde-delivery)<a href="https://agentmods.dev/skills/wingedguardian/genesis-agi/aws-fde-delivery"><img src="https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/aws-fde-delivery/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/skills/wingedguardian/genesis-agi/aws-fde-delivery"><img src="https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/aws-fde-delivery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 136 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00032 | $0.01394 |
| Opus 5 | $0.00016 | $0.00697 |
| Sonnet 5 | $0.00006 | $0.00279 |
| Haiku 4.5 | $0.00003 | $0.00139 |
Grade A, and why
aws-fde-delivery 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AWS FDE Delivery
Purpose
Apply a Forward Deployed Engineer (FDE) delivery model to any AWS engagement: show up with a working system, not a slide deck. An FDE embeds with the problem, builds the thing, and proves it runs on real (or realistically simulated) infrastructure before handing off a recommendation. This skill encodes the mandatory artifact set every AWS deliverable must ship with, the rule for grounding cost claims in real pricing data, and the rule for preferring AWS MCP Servers over raw CLI at the execution layer.
This is a delivery contract, not a technical how-to. It governs what "done" means for an AWS engagement deliverable; pair it with the relevant AWS domain skill (serverless, databases, migration, deployment) for the technical implementation itself.
When to Use
- User asks for an AWS solution proposal, architecture recommendation, or POC for a client, prospect, or internal stakeholder.
- A background task is scoped to "build and deliver" something on AWS, not just describe it.
- Career Ops or portfolio work needs an AWS deliverable that has to survive technical scrutiny (interview take-homes, client pitches, demo requests).
- Any output that will be handed to someone else as the basis for a build-vs-buy or architecture decision.
The Build-First Contract
Slideware is not a deliverable. Every AWS engagement ships all five artifacts below, or explicitly marks the ones it couldn't produce and why. Partial delivery is acceptable; silent omission is not.
1. Code / POC
A runnable implementation of the core mechanism, not pseudocode. It doesn't need full production hardening, but it must actually execute against real AWS APIs (or a documented local emulation, e.g. LocalStack) and produce observable output. If the POC is a Lambda, it must invoke. If it's a data pipeline, it must move real (or representative sample) data end to end.
2. IaC (CDK or CloudFormation)
The deployment must be reproducible from code, not a list of console click-steps. Prefer CDK when the audience is engineering-heavy; use raw CloudFormation when the deliverable needs to be inspectable without a build toolchain. Terraform is acceptable only if the client's existing stack already standardizes on it; state that assumption explicitly.
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.
- 12d ago First seen · 141 lines · 32 tokens per session scan A 0bfc17528a1c
aws-fde-delivery is a skill published in the GitHub repository WingedGuardian/GENesis-AGI (96 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,394 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
distributed-tracing
Implement distributed tracing with Jaeger and Tempo for request flow visibility across microservices.
slo-implementation
Framework for defining and implementing Service Level Indicators (SLIs), Service Level Objectives (SLOs), and error budgets.
workflow-automation
Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off.
incident-responder
Expert SRE incident responder specializing in rapid problem resolution, modern observability, and comprehensive incident management.
cost-benefit-router
Intelligent routing of tasks between Local (OS) and Remote (Cloud) resources based on complexity, privacy, and cost constraints.
observability-stack-setup
Bootstrap end-to-end observability with OpenTelemetry traces, metrics, and logs, including GenAI LLM span conventions, dashboards, alerts, and SLO/SLI definition.