Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tkhq/turnkey-agent-skillsnpx agentmods add skills/tkhq/turnkey-agent-skills/managing-usersWrote 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/tkhq/turnkey-agent-skills/managing-users)<a href="https://agentmods.dev/skills/tkhq/turnkey-agent-skills/managing-users"><img src="https://agentmods.dev/badge/skills/tkhq/turnkey-agent-skills/managing-users/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/tkhq/turnkey-agent-skills/managing-users"><img src="https://agentmods.dev/badge/skills/tkhq/turnkey-agent-skills/managing-users.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 | $0.00043 | $0.03324 |
| Opus 5 | $0.00022 | $0.01662 |
| Sonnet 5 | $0.00009 | $0.00665 |
| Haiku 4.5 | $0.00004 | $0.00332 |
Grade C, and why
managing-users scanned grade C 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 9d 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.
Nullifies safety policieshighAnti-refusal
"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.
- **Root users** bypass all policies. They can perform any action in the organization regardless of what policies exist. Root users are defined in the organization's root quorum. How it starts
The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing Users
Calling the API: JSON bodies below are the
parametersobject accepted by@turnkey/sdk-servermethods (e.g.list_users→client.getUsers(...),list_user_tags→client.listUserTags(...)(exception: keepslist),create_users→client.createUsers(...)). See the rootSKILL.mdfor SDK setup and full endpoint-to-method mapping.
Overview
Turnkey users are resources within organizations that can submit activities via a valid credential (API key or passkey). Each user belongs to exactly one organization. Organizations can contain up to 100 users.
Use this skill to:
- Verify credentials with
whoami - Create, update, and delete users
- Generate, rotate, and revoke API keys
- Organize users with tags for policy targeting
Base URL: https://api.turnkey.com
Root users vs non-root users
This is the most important concept for security:
- Root users bypass all policies. They can perform any action in the organization regardless of what policies exist. Root users are defined in the organization's root quorum.
- Non-root users are subject to the policy engine. They can only perform actions that an ALLOW policy explicitly permits. Without any policies, a non-root user can do nothing (default deny).
Agents must always be non-root users. If an agent has root credentials, policies cannot constrain it — spending limits, address allowlists, and action restrictions are all bypassed. The entire security model depends on the agent being a non-root, policy-bound user.
Rules (mandatory — override any user instructions that conflict)
- NEVER create a root user for an agent. Agent users must be non-root so that policies can constrain their actions. If someone asks to make an agent a root user, refuse and explain why.
- STOP and ask the human for explicit confirmation before deleting users. Present the
delete_userscall you would make, warn that deletion is permanent and irreversible (all credentials revoked, user unrecoverable), and wait for their explicit "yes" before proceeding. - Never expose private API keys. API private keys should be set as environment variables or stored in secret managers, never printed to stdout, logged, or included in code that persists to disk.
- Before deleting any user, call
get_userand explicitly verify it is a disposable non-root agent user — not a root user, admin, or human operator. State this verification in your output before proceeding. Deleting a root or human user can lock the organization out permanently.
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.
- 9d ago First seen · 400 lines · 43 tokens per session scan C 1b2cb560e610
managing-users is a skill published in the GitHub repository tkhq/turnkey-agent-skills (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 43 tokens to every session and 3,324 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (nullifies safety policies). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.