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.
git clone --depth 1 https://github.com/indykite/skillsWrote 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/plugins/indykite/skills/gemini-extension)<a href="https://agentmods.dev/plugins/indykite/skills/gemini-extension"><img src="https://agentmods.dev/badge/plugins/indykite/skills/gemini-extension/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/plugins/indykite/skills/gemini-extension"><img src="https://agentmods.dev/badge/plugins/indykite/skills/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
indykite-skills 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 19d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "indykite-skills",
"version": "1.0.0",
"description": "IndyKite skills for coding agents \u2014 Agent Gateway deployment, MCP server calls, KBAC authorization policy authoring and lifecycle, AuthZEN decisions and search (single evaluation, batch evaluations, action / resource / subject search), runtime listing of a project's active KBAC policies, Capture API ingests and deletes (nodes, relationships, properties, property metadata), IKG data-schema reads, ContX IQ policies / Knowledge Queries / executes (read, create node, create relationship, combined create-with-link, add property, add relationship property, delete), ContX IQ whoami (resolve an end-user token to its IKG subject), and tamper-proof audit log reads and exports.",
"contextFileName": "README.md",
"settings": [
{
"name": "API URL",
"description": "IndyKite REST API base URL for the project's region (e.g. https://us.api.indykite.com or https://eu.api.indykite.com).",
"envVar": "API_URL"
},
{
"name": "AppAgent token (X-IK-ClientKey)",
"description": "AppAgent credentials token. Goes into the X-IK-ClientKey header on every CIQ / MCP call. Mint via POST /configs/v1/application-agent-credentials.",
"envVar": "API_KEY"
},
{
"name": "User OAuth token (Authorization Bearer)",
"description": "User OAuth access token. Required for Person-subject CIQ flows, for ContX IQ whoami, and for MCP session initialisation; omit for _Application-subject flows.",
"envVar": "BEARER_TOKEN"
},
{
"name": "Delegation token (X-IK-Token)",
"description": "Optional delegation token minted by the IndyKite Token Service and forwarded by the Agent Gateway on multi-hop workflows. Goes into the X-IK-Token header next to the user token; only needed to exercise policies that read $ik_token.",
"envVar": "IK_TOKEN"
},
{
"name": "Service Account token",
"description": "Token with Config API write access. UsWhat ships with it
1 file beside gemini-extension.json 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.
- 19d ago Changed · +5 lines f957b522c469
- 1mo ago Changed 31e4573bf883
- 1mo ago First seen · 39 lines scan A e0f86d0c62e0
indykite-skills is a plugin published in the GitHub repository indykite/skills (4 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-08.
Other plugins, from other repositories
app-builder
Development, customization, testing, and deployment skills for Adobe App Builder projects, including the Workfront UI-extension suite (skills/appbuilder-workfront).
load-tester
Load and stress testing for APIs and web services.
rabbitmqadmin
Skill for inspecting RabbitMQ instances using the rabbitmqadmin CLI (rabbitmqadmin-ng).
jpm-payments-skills
Conversational agent skills that walk a merchant from J.P. Morgan Payments onboarding through a working API integration. Supports Checkout and Online Payments in the initial release. Generates language-specific OAuth modules (Node/TypeScript, Python, Java idiomatic; other languages via canonical algorithm).
auth
Auth skills for Claude Code — scaffold hand-rolled auth endpoints and audit auth code against security best practices.
coding
Programming skills: Python, TypeScript, FastAPI, Postgres, coding guidelines, and more.