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-access-scopegit 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-access-scope)<a href="https://agentmods.dev/skills/kong/ai-marketplace/konnect-access-scope"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/konnect-access-scope/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-access-scope"><img src="https://agentmods.dev/badge/skills/kong/ai-marketplace/konnect-access-scope.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 | $0.00063 | $0.01624 |
| Opus 5 | $0.00032 | $0.00812 |
| Sonnet 5 | $0.00013 | $0.00325 |
| Haiku 4.5 | $0.00006 | $0.00162 |
Grade A, and why
konnect-access-scope 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Konnect access and scope troubleshooting
Goal
Explain why an identity can or cannot reach a Konnect surface, see a resource, or mutate it, then identify the narrowest next step.
Default to read-first inspection. Do not propose role or team changes until you have separated resource existence, endpoint selection, authentication, and authorization.
Use this skill for operator or automation access to Konnect itself. Do not use it for downstream API consumer auth, Dev Portal application credentials, or Gateway runtime auth flows.
Tool Selection
- Use the shared
kong-konnectMCP server first for live inspection when it is available in the session. - Use
kongctl-queryfor read-only checks, identity inspection, and resource existence checks from the CLI surface. - Preserve the repository's chosen declarative toolchain when access-adjacent
resources need to be codified: prefer
kongctl-declarativeforkongctlYAML andterraform-konnectfor HCL-managed Konnect resources. - If the request depends on live Konnect state and
kong-konnectMCP is not connected, say so early and continue with CLI or user-provided artifacts.
Do not treat declarative config in a repo as proof that a user should be able to see or edit the live resource. Live access always wins over intended state.
References To Load
Load only the reference file that matches the active branch:
references/region-org-and-team-checks.md- Load when wrong region, org, team, or resource slice is the likely cause.
references/visibility-vs-permission.md- Load when the hard question is whether the resource exists, is visible, or is writable by this identity.
references/idp-and-role-model.md- Load when SSO, SCIM, IdP-managed groups, additive roles, or external identity mastering is the real boundary.
Inspection Order
1. Identify the failing surface
Pin down:
- which interface is failing: MCP,
kongctl, Konnect UI, Konnect API, or Portal operator UI - which operation fails: authenticate, list, get, edit, create, delete
- which resource scope is involved: organization, control plane, portal, catalog asset, analytics surface, or Event Gateway resource
- whether the symptom is "cannot see it" or "can see it but cannot change it"
- whether the caller is a human identity or an automation identity acting directly against Konnect
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 · 192 lines · 63 tokens per session scan A 92afec038f04
konnect-access-scope is a skill published in the GitHub repository Kong/ai-marketplace (5 stars, last pushed 22d ago), licensed MIT. It adds 63 tokens to every session and 1,624 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
adk-debug
Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model. Covers the adk run CLI and the adk web dev server with its session, trace, and debug HTTP endpoints. Use when an agent returns the wrong answer, ignores a tool or swallows a tool error, hangs…
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, Effect v4 CLI tests, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, validating TypeScript package changes, or writing/porting CLI tests against…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
potpie-cli
Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, search, graph workbench reads/writes, and pot scope behavior.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
trulens-diagnosis
Diagnose low evaluation scores and generate actionable improvement recommendations.