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-declarativegit 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-declarative)<a href="https://agentmods.dev/skills/kong/ai-marketplace/kongctl-declarative"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/kongctl-declarative/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-declarative"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/kongctl-declarative.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 | $0.00070 | $0.01512 |
| Opus 5 | $0.00035 | $0.00756 |
| Sonnet 5 | $0.00014 | $0.00302 |
| Haiku 4.5 | $0.00007 | $0.00151 |
Grade A, and why
kongctl-declarative 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kongctl declarative workflows
Goal
Author, update, review, and execute kongctl declarative configuration for
Konnect without drifting into read-only query work or a different declarative
toolchain.
Tool Positioning
- Use this skill when the repository already manages Konnect resources through
kongctlYAML,_defaults.kongctl, orkongctlplan/apply workflows, or when the user explicitly asks forkongctl. - Use the shared
kong-konnectMCP server first when the task depends on live Konnect state and MCP is available. - Use
kongctl-queryfor read-only inspection, exactgetsyntax, output shaping, or CLI-shaped proof that should not mutate state. - Preserve the repository's existing declarative toolchain. Do not convert
decKor Terraform repositories tokongctlunless the user explicitly asks. - Choose execution style from user intent:
- User-run mode: explain the path and give commands.
- Agent-run mode: execute the commands and report results.
References To Load
Load only the branch that matches the task:
references/commands.md- Load for command selection, saved-plan versus inline execution, adopt/dump command shape, output mode behavior, and guardrail flags.
references/resources.md- Load for ownership layout,
_defaults, parent versus child metadata,!file,!ref, and schema discovery.
- Load for ownership layout,
references/apiops-openapi.md- Load when the task generates or updates
apisresources from OpenAPI.
- Load when the task generates or updates
references/cicd-github-actions.md- Load for GitHub Actions validation or deployment workflows.
references/troubleshooting.md- Load when preview or execution fails, or when drift and namespace behavior are unclear.
This skill must stay portable across repositories. Do not assume the upstream
kongctl repo layout or a local docs/ tree.
Validation Contract
Preflight
Before editing manifests or proposing execution:
- Confirm the repository already owns the target Konnect slice through
kongctlrather thandecKor Terraform. - Confirm the CLI is available and authentication works with a small read
command such as
kongctl get organization -o json. - Confirm namespace, profile, file scope, and whether
!fileusage will require--base-dir. - If exact syntax is uncertain, check local help instead of guessing.
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.
- 10d ago First seen · 158 lines · 70 tokens per session scan A 1e70c89ba1ee
kongctl-declarative is a skill published in the GitHub repository Kong/ai-marketplace (5 stars, last pushed 21d ago), licensed MIT. It adds 70 tokens to every session and 1,512 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.
pre-merge
The CI gate. Takes a feature branch from "eng says done" to "PR open against staging with green checks". Runs the project's preflight-resolved pipeline from devkit/policy.json components[]: sync → parallel correctness + security waves → coverage → regression tail → security/migration → PRD-consistency → open PR. Emits…
merge
The ship gate — the only skill that merges. --staging merges the feature→staging PR on green CI, deploys, verifies, emits a human test script and stamps the staging sign-off on approval. --production ships the double-confirmed release to main and deploys production. Never self-certifies staging; nothing reaches main…
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.