indykite-agent-gateway

indykite-agent-gateway is a skill for Claude Code from indykite/skills. It costs 64 tokens per session (2,805 once invoked), scanned A, original, Apache-2.0.

A security gateway placed in front of one agent-to-agent workflow or MCP server. MCP is a protocol that lets AI agents use external tools and services.

In plain words
What is it for?
It helps deploy and configure protected A2A or MCP connections and investigate authorization failures such as HTTP 401 or 403 responses.
Why use it?
It checks who is calling, whether the workflow is allowed, and whether the delegation chain is valid before forwarding requests.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the indykite-skills plugin — 23 skills shipped together

Good fit It helps deploy and configure protected A2A or MCP connections and investigate authorization failures such as HTTP 401 or 403 responses.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/indykite/skills/indykite-agent-gateway
Install

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.

Any agent
npx skills add indykite/skills --skill indykite-agent-gateway
Clone the repo
git clone --depth 1 https://github.com/indykite/skills

Made for: Claude Code.

Or install indykite-skills, the plugin that ships this one along with the rest of its 23 skills.

Wrote 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.

agentmods badge for indykite-agent-gateway

README.md
[![agentmods](https://agentmods.dev/badge/skills/indykite/skills/indykite-agent-gateway/github.svg)](https://agentmods.dev/skills/indykite/skills/indykite-agent-gateway)
Your own site
<a href="https://agentmods.dev/skills/indykite/skills/indykite-agent-gateway"><img src="https://agentmods.dev/badge/skills/indykite/skills/indykite-agent-gateway/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.

agentmods 80×15 button for indykite-agent-gateway

Your own site · 80×15
<a href="https://agentmods.dev/skills/indykite/skills/indykite-agent-gateway"><img src="https://agentmods.dev/badge/skills/indykite/skills/indykite-agent-gateway.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,805 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.02805
Opus 5 $0.00032 $0.01403
Sonnet 5 $0.00013 $0.00561
Haiku 4.5 $0.00006 $0.00281

Measured 11d ago against content hash 201e8711c52f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

indykite-agent-gateway scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

This skill uses generic markdown instructions and works across all agents listed in the [README](../README.md). It does not require Claude Code hooks, Cursor `@`-mentions, Copilot workspace context, or any agent-specific
indykite-agent-gateway/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IndyKite Agent Gateway

The Indykite Agent Gateway (IAG) is a standalone service that protects exactly one downstream - an A2A agent or an MCP server. Deploy one IAG per protected downstream. From the caller's perspective IAG appears as the Target; from the protected downstream's perspective IAG appears as the Source. IAG is not a generic reverse proxy: by default (protocol: a2a) it speaks the A2A protocol and tracks A2A sessions so JSON-RPC streams flow correctly; with protocol: mcp it proxies MCP Streamable HTTP traffic (forwarding Mcp-Session-Id and streaming SSE responses through). Either way the same authorization runs in front.

For each request IAG validates three things:

  1. The caller (token introspection at the IdP).
  2. The workflow (subject CAN_TRIGGER check via AuthZEN/KBAC).
  3. The delegation chain (the request's act chain matches a chain modeled in the IKG).

When to use

Activate this skill when the user:

  • is deploying an agent-to-agent (A2A) workflow and wants policy enforcement in front of each agent;
  • is putting an enforcement point in front of an MCP server (protocol: mcp) so MCP traffic gets the same introspection, AuthZEN check, and audit as A2A;
  • needs traceable user-to-agent delegation through OAuth token exchange and the act chain;
  • is modeling a Workflow and Agent nodes with INVOKES relationships in the IndyKite Graph (IKG);
  • is configuring JARVIS_* environment variables or a config.yaml for one or more IAG instances;
  • is reading IAG audit records (AUTHORIZED / NOT_AUTHORIZED) and trying to explain a 403;
  • is reproducing or extending the iag-demo (A2A) or iag-mcp-demo (A2A + MCP) reference applications.

Do not activate this skill when the user:

  • wants a generic HTTP reverse proxy or service mesh - IAG only speaks A2A or MCP, not arbitrary HTTP;
  • is asking about IndyKite features unrelated to A2A (token introspection alone, plain AuthZEN policies, ContX IQ queries outside of agent gating);
  • is debugging the protected agent itself rather than the gateway in front of it.

Read the full file on GitHub · 161 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 161 lines · 64 tokens per session scan A 201e8711c52f

Subscribe to this mod's changes

indykite-agent-gateway is a skill published in the GitHub repository indykite/skills (4 stars, last pushed 4d ago), licensed Apache-2.0. It adds 64 tokens to every session and 2,805 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens