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 konnect-control-plane-bootstrapgit 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/konnect-control-plane-bootstrap)<a href="https://agentmods.dev/skills/kong/ai-marketplace/konnect-control-plane-bootstrap"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/konnect-control-plane-bootstrap/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/konnect-control-plane-bootstrap"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/konnect-control-plane-bootstrap.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 | $0.00055 | $0.01480 |
| Opus 5.5 | $0.00022 | $0.00592 |
| Sonnet 5.5 | $0.00011 | $0.00296 |
| Haiku 4.5 | $0.00006 | $0.00148 |
Grade A, and why
konnect-control-plane-bootstrap 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Konnect control plane bootstrap
Goal
Help an operator stand up a new Konnect Gateway control plane with the right bootstrap assumptions before the problem becomes Gateway drift or runtime troubleshooting.
Use this skill for initial setup, first-run topology choices, naming, labels, ownership boundaries, and "what should we create first?" decisions. Do not use it for ongoing incident triage, retrofitting generic Gateway config, or fixing an already unhealthy existing control plane unless the missing piece is still bootstrap scope.
Tool Selection
- Use the shared
kong-konnectMCP server first for live inspection of existing control planes, groups, and adjacent Konnect Gateway resources. - If the control plane already exists and the operator is mainly debugging
attachment, health, rollout, or config-application symptoms, hand off to
konnect-gateway-triageinstead of treating the problem as bootstrap. - Preserve the repository's chosen declarative toolchain when bootstrap should
be codified: use
terraform-konnectfor HCL-managed control planes,kongctl-declarativeforkongctlYAML, anddeck-gatewayonly after the control plane exists and the task becomes Gateway-entity configuration. - If the user is following an official quickstart path, keep the quickstart and the durable repo-managed setup distinct in your explanation.
- If live Konnect state matters and
kong-konnectMCP is not connected, say so early and continue with user-provided artifacts or repo context.
References To Load
Load only the reference file that matches the active branch:
references/topology-choice.md- Load when the main question is hosted versus self-hosted data planes, quick local bootstrap versus durable shared environment, or environment shape.
references/bootstrap-artifacts.md- Load when the user needs to separate control plane creation, data plane attachment, and first Gateway config into concrete bootstrap milestones.
references/ownership-boundaries.md- Load when naming, labels, region, repo ownership, or durable management path is the real bootstrap decision.
What ships with it
3 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 · 185 lines · 55 tokens per session scan A 05a52ad58d6a
konnect-control-plane-bootstrap is a skill published in the GitHub repository Kong/ai-marketplace (6 stars, last pushed 10d ago), licensed MIT. It adds 55 tokens to every session and 1,480 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.
konnect-control-plane-bootstrap compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| konnect-control-plane-bootstrapKong/ai-marketplace | Skill | 6 | 10d ago | MIT | A | 55 | 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 |