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 kongctl-querygit 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/kongctl-query)<a href="https://agentmods.dev/skills/kong/ai-marketplace/kongctl-query"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/kongctl-query/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/kongctl-query"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/kongctl-query.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 | $0.00064 | $0.01221 |
| Opus 5 | $0.00032 | $0.00611 |
| Sonnet 5 | $0.00013 | $0.00244 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
kongctl-query 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 12d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kongctl-query
Goal
Use read-only kongctl commands to inspect live Konnect state and return the
smallest command and result slice that actually proves the answer.
Tool Positioning
- Use this skill when the user explicitly wants
kongctl, CLI-shaped proof, or read-only verification after another workflow changed Konnect state. - If the session already has the shared
kong-konnectMCP server and the user needs live inspection more than exact CLI syntax, suggest MCP first and keepkongctlas the fallback proof path. - Do not use this skill for declarative YAML authoring,
kongctlplan/apply/sync, CI/CD scaffolding, or repository refactors. - Preserve the repository's existing delivery toolchain. This skill only owns read paths and post-change verification commands.
References To Load
Load only the branch-specific reference that matches the active problem:
references/resource-discovery.md- Load when the main question is which
kongctl getresource, parent, or child path should be queried.
- Load when the main question is which
references/output-shaping.md- Load when the main question is output mode,
--jq, summarization shape, or formatting surprises from profile or environment defaults.
- Load when the main question is output mode,
references/auth-and-scope-checks.md- Load when auth, profile, region, org scope, or empty results may be the real issue.
Validation Contract
Preflight
- Confirm the CLI is installed and runnable:
kongctl version. - Prefer
kongctl loginfor interactive sessions. Use PAT or SPAT environment variables only when the session is non-interactive. - Never echo, log, or commit token values.
- If the user's org, region, or profile context matters, prove that context
with one org-scoped read such as
kongctl get organization -o jsonbefore reasoning about a missing resource.
Preview
- Choose the smallest read-only command that proves the answer:
kongctl helporkongctl get <resource> --helpfor command shapekongctl get <resource> -o jsonfor list proofkongctl get <resource> "<name-or-id>" -o jsonfor one-object proof- parent-child reads only after the parent boundary is confirmed
- Use explicit
-o jsonunless the user specifically wants YAML. - State the expected slice before relying on filtered or nested output.
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.
- 12d ago First seen · 132 lines · 64 tokens per session scan A e73d591c2f79
kongctl-query is a skill published in the GitHub repository Kong/ai-marketplace (5 stars, last pushed 22d ago), licensed MIT. It adds 64 tokens to every session and 1,221 once invoked, about $0.0003 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
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
API Discoverability for Agents
Making self-hosted services agent-discoverable — bake in a machine-readable API description (OpenAPI spec or a minimal API.md) when building, and discover-first (spec paths, repo search) before probing when integrating.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
cqrs-implementation
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.
workflow-orchestration-patterns
Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
microservices-patterns
Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.