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.
/plugin marketplace add AlexK020908/infra-designer/plugin install infra-designerWrote 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/alexk020908/infra-designer/research-component)<a href="https://agentmods.dev/skills/alexk020908/infra-designer/research-component"><img src="https://agentmods.dev/badge/skills/alexk020908/infra-designer/research-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.
<a href="https://agentmods.dev/skills/alexk020908/infra-designer/research-component"><img src="https://agentmods.dev/badge/skills/alexk020908/infra-designer/research-component.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00105 | $0.01964 |
| Opus 5 | $0.00053 | $0.00982 |
| Sonnet 5 | $0.00021 | $0.00393 |
| Haiku 4.5 | $0.00011 | $0.00196 |
Grade A, and why
research-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 10d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep-research a component from docs
The user wants a new component and has given you a documentation link (a Terraform provider resource page, an AWS service doc, a SaaS API/Terraform doc, …). Your job is to turn that doc into the verified facts needed to author a real component to the contract — by crawling the page, following the links that matter, and distilling what you find — then to hand those facts to the author-component skill, which owns the writing.
This skill is the research half; ../author-component/SKILL.md
is the writing half. Do not duplicate its work — produce a clean research brief and call it.
When to use vs. not
- Use it when the user supplies (or you can find) authoritative docs for a missing capability and you have web access. It's the front door to growing the registry.
- Skip the crawl if
python ${CLAUDE_PLUGIN_ROOT}/engine/cli.py listalready shows a component that covers the need — don't research a duplicate (theaws.elasticache.redistrap). Confirm it's genuinely missing first. - No web access? Stop and say so. Never invent a provider schema from memory — a wrong resource name or argument produces invalid HCL. Fall back to a documented upgrade path.
1. Frame the target (before any crawl)
From the user's prompt + the URL, write down, in one short note:
- What the component is and which provider it belongs to (
aws,cloudflare,datadog, a SaaS, …). A SaaS provisioned via dashboard/CLI rather than Terraform is a handoff component — flag that now (it changesemit). - The canonical Terraform resource(s) you expect, if known (e.g.
aws_opensearch_domain). The Terraform Registry is the source of truth for schema; treat marketing/overview pages as context only. - The questions the component contract forces you to answer — keep these as the crawl's
objective so you fetch with purpose, not breadth for its own sake:
- Exact resource name(s) and required arguments.
- The handful of config knobs a user should set, each with a secure, cheap default.
- Wiring: what IAM actions a caller needs (for
edges.inbound), whether it lives in a VPC behind a security group + its default port (network), and whether a consumer must reference it (provides/injection). - Limits & cost (for
SKILL.md) and audit-able properties (foraudit.yaml). - Extra Terraform providers it needs (
requires, e.g.random).
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.
- 10d ago First seen · 139 lines · 105 tokens per session scan A d8c59af5c0a0
research-component is a skill published in the GitHub repository AlexK020908/infra-designer (2 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 1,964 once invoked, about $0.0005 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
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
officecli-data-dashboard
Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to…
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
gpt-image-2
A skill for generating or editing images with GPT Image 2 across local, host-provided, or advisory setups.