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 gateway-plugin-datakitgit 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/gateway-plugin-datakit)<a href="https://agentmods.dev/skills/kong/ai-marketplace/gateway-plugin-datakit"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/gateway-plugin-datakit/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/gateway-plugin-datakit"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/gateway-plugin-datakit.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 | $0.00057 | $0.01321 |
| Opus 5.5 | $0.00023 | $0.00528 |
| Sonnet 5.5 | $0.00011 | $0.00264 |
| Haiku 4.5 | $0.00006 | $0.00132 |
Grade A, and why
gateway-plugin-datakit 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Help the agent turn an orchestration request into a correct DataKit flow, or debug an existing flow, without drifting into generic Gateway or declarative tool guidance.
Own DataKit reasoning: phase choice, node selection, DAG structure, connection shape, cache or vault requirements, and debug strategy.
Tool Selection
Prefer working from the artifact that already owns the flow:
- If the repo already contains DataKit YAML under
deck,kong.yaml, or other declarative config, edit that artifact in place. - If the request depends on current Konnect state and
kong-konnectMCP is available, use it to inspect the attached plugin instance and confirm whether the problem is in the saved config or only in the repo copy. - If the request is only about DataKit flow behavior, stay in this skill. Hand
off only when the work becomes mainly about
decK,kongctl, or Terraform packaging.
References To Load
Load only the file that matches the current branch:
references/node-reference.md- Load when choosing node types, checking required fields, or confirming what a node or implicit object can read or write.
references/patterns.md- Load when translating a user workflow into a starter flow shape such as fan-out merge, auth injection, caching, XML conversion, dynamic URLs, or header mutation.
references/resources-and-debugging.md- Load when the problem depends on cache or vault resources, live debug traces, deployment topology, or version-gated behavior.
Run scripts/validate_datakit_flow.py when a local YAML file already exists
and you need deterministic checks for node naming, references, branch targets,
cycles, implicit-field misuse, or missing cache or vault resources.
Workflow
- Classify the request before drafting YAML.
- Identify whether the flow runs in access or response phase.
- Confirm whether the plugin should mutate
service_request, mutateresponse, or short-circuit withexit. - Confirm the attachment boundary: service, route, consumer, consumer group, or global.
What ships with it
4 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 · 135 lines · 57 tokens per session scan A cc0f0f7fe5d2
gateway-plugin-datakit is a skill published in the GitHub repository Kong/ai-marketplace (6 stars, last pushed 10d ago), licensed MIT. It adds 57 tokens to every session and 1,321 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.
gateway-plugin-datakit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gateway-plugin-datakitKong/ai-marketplace | Skill | 6 | 10d ago | MIT | A | 57 | Claude Code |
| eveComposioHQ/composio | Skill | 31k | yesterday | MIT | A | 47 | Claude Code, Codex |
| azure-messagingmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 178 | Claude Code |
| database-rds-devopsaws/tools-for-devops-agent | Skill | 137 | yesterday | Apache-2.0 | A | 75 | Claude Code, Codex |
| iii-observeiii-hq/iii | Skill | 19k | yesterday | none | A | 66 | Claude Code, Codex |
| iii-error-handlingiii-hq/iii | Skill | 19k | yesterday | none | A | 47 | Claude Code, Codex |
| guardrails-developer-guideNVIDIA-NeMo/Guardrails | Skill | 7.4k | yesterday | none | A | 92 | Claude Code, Codex |