author-component

author-component is a skill for Claude Code from AlexK020908/infra-designer. It costs 81 tokens per session (1,758 once invoked), scanned A, original, MIT.

A workflow for creating a new reusable infrastructure building block when the existing component registry has no suitable one.

In plain words
What is it for?
It helps research a Terraform provider schema, write and register a four-file component, and validate it against the project contract.
Why use it?
It prevents missing infrastructure needs from being silently dropped or handled with an unsuitable component.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the infra-designer plugin — 19 skills, 5 commands shipped together

Good fit It helps research a Terraform provider schema, write and register a four-file component, and validate it against the project contract.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add AlexK020908/infra-designer
Claude Code
/plugin install infra-designer

Made for: Claude Code.

Or install infra-designer, the plugin that ships this one along with the rest of its 19 skills, 5 commands.

Wrote 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.

agentmods badge for author-component

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexk020908/infra-designer/author-component/github.svg)](https://agentmods.dev/skills/alexk020908/infra-designer/author-component)
Your own site
<a href="https://agentmods.dev/skills/alexk020908/infra-designer/author-component"><img src="https://agentmods.dev/badge/skills/alexk020908/infra-designer/author-component/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.

agentmods 80×15 button for author-component

Your own site · 80×15
<a href="https://agentmods.dev/skills/alexk020908/infra-designer/author-component"><img src="https://agentmods.dev/badge/skills/alexk020908/infra-designer/author-component.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,758 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00081 $0.01758
Opus 5 $0.00041 $0.00879
Sonnet 5 $0.00016 $0.00352
Haiku 4.5 $0.00008 $0.00176

Measured 9d ago against content hash 3914a424521b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

author-component 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 9d 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.

infra-plugin/skills/author-component/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authoring a missing component

When a design genuinely needs a capability and python ${CLAUDE_PLUGIN_ROOT}/engine/cli.py list shows no matching component, do not silently drop it or avoid it. Author a real, thorough component that follows the contract, then use it like any other. Only fall back to a documented "named upgrade path" (a note in decisions, not a node) if you genuinely cannot author it — e.g. no web access to verify the provider's resource schema.

This is the one sanctioned way to add a type that isn't already in components/.

0. Confirm it's actually missing and worth adding

  • cli.py list and skim components/<provider>/ — make sure no existing component covers it (e.g. don't add "cache" if aws.elasticache.redis fits).
  • A component must be a reusable building block, not a one-off. If it's truly bespoke, prefer composing existing components.

1. Research before writing (be thorough)

Working from a documentation URL? Use the research-component skill (skills/research-component/SKILL.md) for this step — it crawls the doc page, fans out subagents over the relevant subpages, and hands back a verified research brief. Return here with that brief for steps 2–5.

  1. Read the contract end to end: components/CONTRACT.md. It is the source of truth for every field and convention below.
  2. Mirror two existing components of the closest shape as templates — read all four files of each:
    • a compute one (aws/ecs-service or aws/lambda-function) if it runs code,
    • a store/managed one (aws/dynamodb-table, aws/s3-bucket) if it holds data,
    • a network one (aws/rds-postgres) if it lives in the VPC behind a security group,
    • an external/SaaS one (web/frontend, supabase/database) if it's not AWS IaC.
  3. Look up the real Terraform resources on the Terraform Registry (registry.terraform.io → the provider → Resources): get the exact resource names, required arguments, and sane defaults. Prefer raw resource blocks; wrap a registry module only for genuinely complex things (VPC, EKS). Verify against the provider's own docs — never copy from third-party blog snippets.
  4. Note cross-resource needs. Some components need a resource that lives on another node (e.g. CloudFront needs an S3 bucket policy that references the distribution ARN — "reverse injection"). The contract's provides/inbound injection covers a target referencing a source; if you need the opposite, emit the dependent resource from the component that owns it and reference across with a documented convention, or note the limitation in the component's SKILL.md.

Read the full file on GitHub · 118 lines

Changes

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.

  1. 9d ago First seen · 118 lines · 81 tokens per session scan A 3914a424521b

Subscribe to this mod's changes

author-component is a skill published in the GitHub repository AlexK020908/infra-designer (2 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 1,758 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 2026-08-31.

Related

Other skills, from other repositories

terraform-skill

Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…

agentscope-ai/QwenPaw · 62 tokens

terraform-cli-setup

A setup guide for installing and initializing Terraform, a tool for managing infrastructure from configuration files. It also covers basic provider downloads and mirror settings, but not cloud-provider credentials.

agentscope-ai/QwenPaw · 58 tokens

alicloud_cli

A Chinese-language reference for the Alibaba Cloud command-line tool, which lets developers manage Alibaba Cloud services from a terminal. It uses an offline copy of the documentation as its main source.

agentscope-ai/QwenPaw · 45 tokens

deploy

A deployment workflow for putting Rails applications online using Railway, a hosting service.

clacky-ai/openclacky · 0 tokens

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.

clacky-ai/openclacky · 40 tokens

webflow-cli:cloud

Create, build, and deploy Webflow Cloud apps from the CLI (site-attached or project apps), and manage existing ones — apps, domains, environments, deployments, build/runtime logs, and environment variables including secrets. Use when initializing or deploying a Cloud app, importing an existing GitHub repository…

webflow/webflow-skills · 134 tokens