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/aws-controllers-k8s/ack-dev-skills/ack-devnpx skills add aws-controllers-k8s/ack-dev-skills --skill ack-devgit clone --depth 1 https://github.com/aws-controllers-k8s/ack-dev-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/skills/aws-controllers-k8s/ack-dev-skills/ack-dev)<a href="https://agentmods.dev/skills/aws-controllers-k8s/ack-dev-skills/ack-dev"><img src="https://agentmods.dev/badge/skills/aws-controllers-k8s/ack-dev-skills/ack-dev.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 | $0.00070 | $0.04116 |
| Opus 5 | $0.00035 | $0.02058 |
| Sonnet 5 | $0.00014 | $0.00823 |
| Haiku 4.5 | $0.00007 | $0.00412 |
Grade A, and why
ack-dev 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 4d 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 — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACK Development Guide
Overview
AWS Controllers for Kubernetes (ACK) lets you manage AWS resources directly from Kubernetes. It consists of three components:
- Runtime - Shared library: base controller logic, AWS SDK integration, reconciliation framework
- Code Generator - Generates CRDs, Go types, controller logic, and SDK bindings from AWS API models
- Service Controllers - Individual controllers per AWS service, built from generated code + custom hooks
AWS API Model → Code Generator → Generated Code → Controller
↓ ↓ ↓
service.json generator.yaml CRDs + Go types
Working Conventions
- Use available resources - Ask if local clones of upstream repos are available before trying to fetch remote content.
- Feed the skill - When you discover gaps, new patterns, or fixes not covered here, propose updating the relevant file in this skill (SKILL.md or references/). Capture what you learned so the next session benefits.
Golden Rules
These apply everywhere. They are not repeated in individual sections.
Never use aws-sdk-go v1. The Go module github.com/aws/aws-sdk-go (no -v2 suffix) is deprecated. ACK uses github.com/aws/aws-sdk-go-v2. When looking for API models, SDK types, or operation definitions, always use the v2 module paths. The AWS_SDK_GO_VERSION env var below refers to the Go module version of the v2 SDK (e.g., v1.41.0 is the module version, not the SDK generation).
Never manually edit generated files. All files in apis/v1alpha1/, pkg/resource/, config/crd/, config/rbac/, helm/, and cmd/controller/main.go are generated and will be overwritten. If something's wrong, fix generator.yaml and rebuild.
Edit only these:
generator.yaml- All resource configurationtemplates/hooks/- Custom hook templates (if needed)test/e2e/- E2E tests
Always use make build-controller from the code-generator directory. It handles everything in one shot: API types, controller code, deepcopy, CRDs, RBAC, Helm chart, gofmt, and go mod tidy. Individual ack-generate commands can leave partial state.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/code-generation.md 6.4 KB
- references/contributing-codegen.md 2.2 KB
- references/environment-setup.md 1.3 KB
- references/pr-workflow.md 6.0 KB
- references/running-e2e-tests.md 6.7 KB
- references/testing.md 4.4 KB
- references/troubleshooting.md 5.1 KB
- scripts/build-controller.sh 1.3 KB runs code
- scripts/setup-e2e.sh 1.1 KB runs code
- scripts/verify-build.sh 1.7 KB runs code
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.
- 4d ago First seen · 389 lines · 70 tokens per session scan A c1472bbdac30
ack-dev is a skill published in the GitHub repository aws-controllers-k8s/ack-dev-skills (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 4,116 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 skills, from other repositories
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…
rule
Skill "rule" from x-cmd/x-cmd, covering rule — rules to rule, 核心命令, 规则文件格式, 示例 and 验证规则文件格式.
cve
Look up CVE records via x cve — cached, zero-API-key, daily xz TSV. Load for cve, vulnerability id, kev, epss, nvd, cvelist, or security advisory.
azmon-mirroredcatalogs-operations-cli
Brings Azure Monitor, Application Insights, and Log Analytics telemetry into Fabric as Eventhouse external delta tables and correlates it with business data. Use to onboard observability data, judge whether latency or availability affected revenue, or build a Real-Time dashboard and Operations Agent over it.
atmos-auth
Authentication and identity management: providers (SSO/SAML/OIDC/GCP/Atmos Pro), identities, keyring, identity chaining, login/exec/shell/console, and github/sts for private GitHub access.
terraform-search-import
Discover existing cloud resources using Terraform Search queries and bulk import them into Terraform management. Use when bringing unmanaged infrastructure under Terraform control, auditing cloud resources, or migrating to IaC.