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 Kong/ai-marketplace --skill terraform-konnectgit clone --depth 1 https://github.com/Kong/ai-marketplaceWrote 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/kong/ai-marketplace/terraform-konnect)<a href="https://agentmods.dev/skills/kong/ai-marketplace/terraform-konnect"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/terraform-konnect/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/kong/ai-marketplace/terraform-konnect"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/terraform-konnect.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 | $0.00059 | $0.02441 |
| Opus 5.5 | $0.00024 | $0.00976 |
| Sonnet 5.5 | $0.00012 | $0.00488 |
| Haiku 4.5 | $0.00006 | $0.00244 |
Grade A, and why
terraform-konnect 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 2mo 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terraform for Konnect
Goal
Author and maintain Konnect resources in HCL using the official Terraform provider while preserving the repository's existing module, state, and CI conventions.
Use this skill for Terraform-managed Konnect work. Do not turn a kongctl or
decK repository into Terraform unless the user asks for that migration. Do
not treat this skill as the owner for generic backend, state-locking, or
provider-install issues unless they directly block Konnect resource work.
Tool Positioning
- Use the shared
kong-konnectMCP server first for live Konnect inspection when the requested change depends on current state and MCP is available. - Use this skill when the repository already uses Terraform for Konnect or the user explicitly asks for HCL, Terraform Cloud, plan/apply, or provider-based management.
- Preserve existing Terraform layout, backend configuration, module structure, and variable conventions.
- Prefer the official
kong/konnectprovider by default and treatkong/konnect-betaas an explicit exception for missing coverage. - Hand off to
deck-gatewaywhen the user wants file-based Gateway GitOps ordecKexport/diff workflows. - Hand off to
kongctl-declarativewhen the repository already useskongctlYAML instead of HCL. - Hand off to the relevant Konnect domain skill when the main problem is access, publication, runtime health, or another product diagnosis rather than HCL ownership.
References To Load
Load only the reference file that matches the active branch:
references/provider-selection.md- Load when deciding whether the official
kong/konnectprovider is enough or whether the user explicitly needskong/konnect-beta.
- Load when deciding whether the official
references/import-moved-and-adoption.md- Load when existing Konnect resources must be normalized into Terraform state rather than recreated.
references/module-boundaries.md- Load when the main question is where a new Konnect resource belongs in an existing Terraform layout.
references/gateway-entities-inside-konnect.md- Load when the task mixes Konnect platform resources with Gateway entities inside a Konnect control plane.
references/provider-schema-debugging.md- Load when nested resource shape is unclear, validation reports object-vs-string or similar type mismatches, or provider behavior does not line up cleanly with docs or example HCL.
What ships with it
5 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.
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.
- 2mo ago First seen · 281 lines · 59 tokens per session scan A 74c72bafabf9
terraform-konnect is a skill published in the GitHub repository Kong/ai-marketplace (6 stars, last pushed 10d ago), licensed MIT. It adds 59 tokens to every session and 2,441 once invoked, about $0.0002 per session on Opus 5.5. 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.
terraform-konnect compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| terraform-konnectKong/ai-marketplace | Skill | 6 | 10d ago | MIT | A | 59 | Claude Code |
| orchard-releaserohitg00/ai-engineering-from-scratch | Skill | 77k | yesterday | MIT | A | 11 | Claude Code, Codex |
| azure-mgmt-fabric-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 88 | Claude Code |
| azure-resource-manager-durabletask-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 84 | Claude Code |
| azure-eventhub-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 94 | Claude Code |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| azure-resource-manager-sql-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 109 | Claude Code |