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/cloudposse/atmos/atmos-core-component-developmentnpx skills add cloudposse/atmos --skill atmos-core-component-developmentgit clone --depth 1 https://github.com/cloudposse/atmosWrote 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/cloudposse/atmos/atmos-core-component-development)<a href="https://agentmods.dev/skills/cloudposse/atmos/atmos-core-component-development"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/atmos-core-component-development.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 | $0.00080 | $0.01403 |
| Opus 5 | $0.00040 | $0.00701 |
| Sonnet 5 | $0.00016 | $0.00281 |
| Haiku 4.5 | $0.00008 | $0.00140 |
Grade A, and why
atmos-core-component-development 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atmos Core: Component Type Development
Use this skill when developing Atmos itself — adding or modifying a component type (kind) in the
Go codebase. This is contributor/core guidance, distinct from the user-facing atmos-components skill
(which documents authoring terraform/helmfile/container components in stacks).
Start from docs/developing-component-plugins.md (the component-plugin development guide). The notes
below capture the non-obvious wiring learned while adding the container component type.
The component provider (pkg/component)
A component type is a ComponentProvider (pkg/component/provider.go) registered via init() with
component.Register(...) (pkg/component/registry.go). Reference impls:
pkg/component/ansible/— typed-config built-in style.pkg/component/mock/,pkg/component/custom/— thePlugins-map plugin style.pkg/component/container/— provider +cmd/lifecycle split.
Layout per the guide: config.go (typed Config + parseConfig), <type>.go (provider + init),
executor.go (verb implementations), <type>_test.go (>90% coverage). Wire a blank import into
cmd/root.go so init() runs.
Reusable error sentinels live in errors/errors.go: ErrComponentExecutionFailed,
ErrComponentConfigInvalid, ErrComponentValidationFailed, ErrComponentTypeEmpty.
First-class component config (NOT vars)
Per-instance config that is not arbitrary template data must be first-class top-level sections
(siblings of metadata/env/composition), NOT nested under vars. For container, the config reuses
the workflow container-step structs (schema.ContainerBuildStep/ContainerRunStep/ContainerMount/
ContainerPort in pkg/schema/workflow.go) for consistency. Decode a YAML-derived map[string]any
into those structs with mapstructure using TagName: "yaml" so snake_case keys (build_args,
read_only) map.
The CLI command group (cmd/)
Mirror cmd/ansible/: a base cobra.Command registered through the command registry
(cmd/internal CommandProvider), persistent flags via flags.NewStandardParser() (NEVER
viper.BindEnv/BindPFlag), one thin file per verb dispatching to
component.MustGetProvider(<type>).Execute(&component.ExecutionContext{...}). Wire a blank import into
cmd/root.go.
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 · 96 lines · 80 tokens per session scan A 5ce757a76fcf
atmos-core-component-development is a skill published in the GitHub repository cloudposse/atmos (1,369 stars, last pushed today), licensed Apache-2.0. It adds 80 tokens to every session and 1,403 once invoked, about $0.0004 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
dstack-prototyping
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final…
dstack-presets
Create and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format. Use together with the dstack skill, and only when the user explicitly asks to create a preset or manage existing presets, not for deploying or serving a model.
dstack
Skill "dstack" from dstackai/dstack, covering dstack, how it works, quick agent flow (detached runs), agent execution guidelines and output accuracy.
flow-nexus-swarm
Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform.
Agentic Orchestration for Oracle
Multi-agent coordination patterns for enterprise AI systems on Oracle Cloud Infrastructure.
Oracle ADK Expert
Build production agentic applications on OCI using Oracle Agent Development Kit with multi-agent orchestration, function tools, and enterprise patterns.